CN117314771A - Belt artifact processing method and device, electronic equipment and storage medium - Google Patents
Belt artifact processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117314771A CN117314771A CN202311139486.2A CN202311139486A CN117314771A CN 117314771 A CN117314771 A CN 117314771A CN 202311139486 A CN202311139486 A CN 202311139486A CN 117314771 A CN117314771 A CN 117314771A
- Authority
- CN
- China
- Prior art keywords
- preset
- belt
- target pixel
- pixel point
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 6
- 238000001914 filtration Methods 0.000 claims abstract description 151
- 238000007689 inspection Methods 0.000 claims abstract description 69
- 238000012937 correction Methods 0.000 claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 59
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 241000566145 Otus Species 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides a processing method, a device, electronic equipment and a storage medium for belt artifact, wherein the electronic equipment can acquire image data to be processed of security inspection equipment aiming at an inspected object; in a preset filter kernel sliding process, determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on a gray value of a target pixel point in the image data to be processed; and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed detected object. The gray values of the pixel points corresponding to the filtering units included in the filtering kernel can reflect the characteristics of the pixel points corresponding to the filtering kernel more comprehensively, so that the belt artifact pixels are determined based on the gray values of the target pixel points, and the pixel points corresponding to the detected object can be prevented from being determined as the belt artifact pixels. Therefore, the imaging quality of the security inspection machine can be improved, and the problem of belt artifact in a general scene can be stably solved.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and apparatus for processing belt artifacts, an electronic device, and a storage medium.
Background
Currently, an X-ray security inspection machine generally uses an L-shaped linear array detector, and line scanning imaging of an object is achieved through uniform movement of a belt carrier. Under ideal conditions, correction parameters of the detector module can be calculated through a bright field template and a dark field template of the detector, and the influence of the belt on the imaging of the security inspection machine is removed by utilizing bright field correction and offset correction. However, due to the deviation of production and manufacture and installation and debugging of the belt roller, the deviation of the belt in the radial direction of the roller in the long-term rotation process, or the abrasion of local areas such as edges of the belt in the long-term operation process, the deviation of the bright field template and the dark field template of the local detector pixels is caused, and finally, random continuous slender artifacts are generated in the image correction process.
In order to treat belt artifacts, more common ways are divided into pre-treatment and post-treatment: the preprocessing mode starts from the root cause of belt artifact, and because the bright field template and the dark field template stored in the early stage are not matched with the current data, the bright field template is updated immediately after each time of source opening, and the stably-appearing belt artifact caused by structural installation errors can be removed relatively effectively. For the post-processing mode, the processing can be performed by using a mode of combining edge detection with morphology.
With the pretreatment mode, artifacts caused by random radial offset of the belt rollers cannot be treated, and the risk of serious artifact problems caused by premature updating of the bright field template due to inconsistent performance of the ray source exists. By adopting the post-processing mode, a large amount of image main body information is lost, so that the situation of misjudgment and missed judgment of key articles is caused, and the calculation time consumption is difficult to meet the requirement of real-time processing under the condition of low calculation resources. Therefore, the effect of processing the belt artifact is poor at present, and the problem of the belt artifact in a general scene is difficult to stably solve.
Disclosure of Invention
An embodiment of the application aims to provide a processing method and device for belt artifacts, electronic equipment and a storage medium, so as to stably solve the problem of belt artifacts in a general scene. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for processing a belt artifact, where the method includes:
acquiring image data to be processed of security inspection equipment aiming at an inspected object;
in a preset filtering kernel sliding process, determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on a gray value of a target pixel point in the image data to be processed, wherein the target pixel point is a pixel point corresponding to a plurality of filtering units included in the preset filtering kernel in the image data to be processed, the preset filtering kernel further comprises an expansion unit, and the filtering units and the expansion unit are arranged at intervals;
And carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed object to be inspected.
Optionally, in the sliding process of the preset filter kernel, the step of determining whether each pixel point in the image data to be processed is a belt artifact pixel based on the gray value of the target pixel point in the image data to be processed includes:
sliding a preset filter kernel with a fixed step length according to the storage sequence of the image data to be processed in the memory;
each time the preset filter kernel is slid, determining whether the center target pixel point is a belt artifact pixel according to the relation between the center target pixel point and the edge target pixel point in the image data to be processed and a preset threshold condition respectively and the number of other target pixel points meeting the preset threshold condition;
the center target pixel point is a pixel point corresponding to a center filter unit of the preset filter core, the edge target pixel point is a pixel point corresponding to an edge filter unit of the preset filter core, and the other target pixel points are pixel points corresponding to filter units except the center filter unit and the edge filter unit.
Optionally, the step of determining whether the center target pixel point is a belt artifact pixel according to the relationship between the center target pixel point and the edge target pixel point in the image data to be processed and the preset threshold condition, and the number of other target pixel points meeting the preset threshold condition, includes:
judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value or not;
if the gray value of the central target pixel point is smaller than the preset gray value threshold, determining whether the gray values of the other target pixel points are smaller than the preset gray value threshold;
if the gray value of the other target pixel points is smaller than the preset gray value threshold, determining whether the number of the target pixel points with the corresponding gray values smaller than the preset gray value threshold is not larger than a preset number;
if the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than the preset number, determining whether the gray value of the edge target pixel points is larger than the preset gray value threshold;
and if the gray value of the edge target pixel point is larger than the preset gray value threshold, determining that the center target pixel point is a belt artifact pixel.
Optionally, the number of the plurality of filtering units included in the preset filtering core and the length of the expansion unit are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering core is greater than the length of the belt artifact to be detected.
Optionally, the preset filter kernel includes a number of filter units of 5, and the preset number is 2.
Optionally, the step of acquiring the image data to be processed of the security inspection device for the inspected object includes:
acquiring a bright field template, a dark field template and image data to be processed of an inspected object of security inspection equipment, wherein the bright field template is the X-ray signal intensity acquired by a detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is stationary, and the dark field template is the X-ray signal intensity acquired by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is stationary;
based on the bright field template, the dark field template and the image data to be processed, calculating a gray value Cali of the pixel point according to the following formula n :
R n =Air n -Bk n
Wherein, air n Bk for the bright field template data n For the dark field template data, scann n Bk for the image data to be processed n For the dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor.
Optionally, the step of performing gray correction on the belt pseudo-image element to generate a security inspection image corresponding to the processed object to be inspected includes:
after all belt pseudo-image pixels included in the image data to be processed are determined, gray level correction is carried out on each belt pseudo-image pixel, and a security inspection image corresponding to the detected object after processing is generated;
or alternatively
Obtaining duplicate data which is completely the same as the image data to be processed;
determining artifact pixels in the copied data corresponding to the belt artifact pixels in the image data to be processed based on the detected belt artifact pixels in the image data to be processed;
and carrying out gray scale correction on the pseudo-image pixels in the copied data to generate a security inspection image corresponding to the processed object to be inspected.
In a second aspect, an embodiment of the present application provides a device for processing belt artifact, where the device includes:
the data acquisition module is used for acquiring image data to be processed of the security inspection equipment aiming at the inspected object;
the pixel determining module is used for determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on a gray value of a target pixel point in the image data to be processed in a preset filter kernel sliding process, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, and the filter units and the expansion unit are arranged at intervals;
And the gray level correction module is used for carrying out gray level correction on the belt pseudo-image pixels and generating a processed security check image corresponding to the detected object.
Optionally, the pixel determining module includes:
the filtering core sliding sub-module is used for sliding a preset filtering core in a fixed step length according to the storage sequence of the image data to be processed in the memory;
the pixel determining submodule is used for determining whether the central target pixel point is a belt artifact pixel or not according to the relation between the central target pixel point and the edge target pixel point in the image data to be processed and a preset threshold condition respectively and the number of other target pixel points meeting the preset threshold condition once sliding the preset filter kernel;
the center target pixel point is a pixel point corresponding to a center filter unit of the preset filter core, the edge target pixel point is a pixel point corresponding to an edge filter unit of the preset filter core, and the other target pixel points are pixel points corresponding to filter units except the center filter unit and the edge filter unit.
Optionally, the pixel determining submodule includes:
The central target pixel point judging unit is used for judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value or not;
the other target pixel point judging unit is used for determining whether the gray value of the other target pixel points is smaller than the preset gray value threshold value or not if the gray value of the central target pixel point is smaller than the preset gray value threshold value;
a number determining unit configured to determine, if the gray value of the other target pixel point is smaller than the preset gray value threshold, whether the number of target pixel points whose corresponding gray values are smaller than the preset gray value threshold is not greater than a preset number;
an edge target pixel point judging unit, configured to determine whether a gray value of the edge target pixel point is greater than the preset gray value threshold if the number of target pixel points corresponding to the gray value being less than the preset gray value threshold is not greater than the preset number;
and the pixel determining unit is used for determining that the central target pixel point is a belt artifact pixel if the gray value of the edge target pixel point is larger than the preset gray value threshold value.
Optionally, the number of the plurality of filtering units included in the preset filtering core and the length of the expansion unit are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering core is greater than the length of the belt artifact to be detected.
Optionally, the preset filter kernel includes a number of filter units of 5, and the preset number is 2.
Optionally, the data acquisition module includes:
the data acquisition sub-module is used for acquiring a bright field template, a dark field template and image data to be processed of an object to be detected of the security inspection equipment, wherein the bright field template is the X-ray signal intensity acquired by a detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is stationary, and the dark field template is the X-ray signal intensity acquired by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is stationary;
a gray value calculation sub-module for calculating gray values Cali of the pixel points according to the following formula based on the bright field template, the dark field template and the image data to be processed n :
R n =Air n -Bk n
Wherein, air n Bk for the bright field template data n Scan for the dark field template data n Bk for the image data to be processed n For the dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor.
Optionally, the gray-scale correction module is configured to perform gray-scale correction on each belt pseudo-image element after determining all belt pseudo-image elements included in the image data to be processed, so as to generate a security check map corresponding to the detected object after processing; or, the gray correction module is configured to: obtaining duplicate data which is completely the same as the image data to be processed; determining an artifact pixel point in the copy data corresponding to the belt artifact pixel in the image data to be processed based on the detected belt artifact pixel in the image data to be processed; and carrying out gray correction on the pseudo image pixels in the copied data to generate a security check image corresponding to the processed object to be checked.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory for storing a computer program;
a processor configured to implement the method according to any one of the first aspect when executing a program stored in the memory.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, which when executed by a processor implements the method of any of the first aspects.
The beneficial effects of the embodiment of the application are that:
in the scheme provided by the embodiment of the application, the electronic equipment can acquire the image data to be processed of the security inspection equipment aiming at the inspected object; in the sliding process of the preset filter kernel, based on the gray value of a target pixel point in the image data to be processed, determining whether each pixel point in the image data to be processed is a belt artifact pixel, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, the filter units and the expansion unit are arranged at intervals, and the more obvious belt artifact can be processed under the condition of not increasing the calculated amount additionally; and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed detected object. The gray values of the pixel points corresponding to the filtering units included in the filtering kernel can reflect the characteristics of the pixel points corresponding to the filtering kernel more comprehensively, so that the belt artifact pixels are determined based on the gray values of the target pixel points, and the pixel points corresponding to the detected object can be prevented from being determined as the belt artifact pixels. The belt artifact can be rapidly and accurately processed by the scheme, the imaging quality of the security inspection machine is improved, and the problem of the belt artifact under a general scene is stably solved.
Of course, not all of the above-described advantages need be achieved simultaneously in practicing any one of the products or methods of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other embodiments may also be obtained according to these drawings to those skilled in the art.
FIG. 1 is a sectional view of a security inspection apparatus according to the related art;
FIG. 2 is a schematic diagram of an image corresponding to an object generated by the prior art;
FIG. 3 is a flowchart of a method for processing belt artifacts according to an embodiment of the present disclosure;
FIG. 4 is a flowchart showing a step S302 in the embodiment shown in FIG. 3;
FIG. 5 is a first schematic diagram of belt artifact detection according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a filter core including an expansion unit according to an embodiment of the present application;
FIG. 7 is a flowchart showing a step S402 in the embodiment shown in FIG. 4;
FIG. 8 is a schematic diagram of determining belt artifact pixels based on the filter kernel of FIG. 6;
FIG. 9 (a) is a second schematic diagram of belt artifact detection according to an embodiment of the present application;
FIG. 9 (b) is a third schematic diagram of belt artifact detection according to an embodiment of the present application;
fig. 10 is a schematic diagram of an image corresponding to an object to be tested generated by using the belt artifact processing method provided in the embodiment of the present application;
fig. 11 is a schematic structural diagram of a belt artifact processing apparatus according to an embodiment of the present disclosure;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. Based on the embodiments herein, a person of ordinary skill in the art would be able to obtain all other embodiments based on the disclosure herein, which are within the scope of the disclosure herein.
In the related art, a cut-out view of a security inspection device may be shown in fig. 1. For the security inspection device shown in fig. 1, an object to be inspected can be placed on the upper surface of the belt 101, during the process that the object to be inspected moves along with the belt 101, the ray source 102 can emit rays, and the rays are collected by the detectors 103 in the L-shaped detector group after passing through the belt 101 and the object to be inspected placed thereon. Therefore, the gray value of each pixel point in the image data can be determined according to the intensity of the X-ray signal acquired by the detector, and then the image corresponding to the detected object is generated.
Since the belt 101 is worn in its edge region during long-term operation. Therefore, after the detector region 104 collects the radiation passing through the edge region of the belt 101, belt artifacts are easily formed in the generated image corresponding to the subject.
With the related art, a schematic diagram of the generated image corresponding to the subject may be shown in fig. 2. Region 201 is the region where the belt artifact is located and there is more noise in the image.
To stably solve the problem of belt artifact in a general scene. Embodiments of the present application provide a method, apparatus, electronic device, computer readable storage medium, and computer program product for processing belt artifact. The following first describes a method for processing belt artifacts provided in the embodiments of the present application.
The method for processing the belt artifact provided by the embodiment of the application can be applied to any electronic equipment needing to process the belt artifact, for example, subway security check equipment, airport security check equipment and the like, and is not particularly limited. For clarity of description, hereinafter referred to as an electronic device.
As shown in fig. 3, a method for processing belt artifacts, the method comprising:
S301, obtaining image data to be processed of security inspection equipment aiming at an inspected object;
s302, in the sliding process of a preset filtering kernel, determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on the gray value of the target pixel point in the image data to be processed;
the target pixel points are pixel points corresponding to a plurality of filtering units included in the preset filtering core in the image data to be processed, the preset filtering core further comprises an expansion unit, and the filtering units and the expansion unit are arranged at intervals.
And S303, carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed object to be inspected.
In the embodiment of the application, the electronic device may acquire the image data to be processed of the security inspection device for the inspected object; in the sliding process of the preset filter kernel, based on the gray value of a target pixel point in the image data to be processed, determining whether each pixel point in the image data to be processed is a belt artifact pixel, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, the filter units and the expansion unit are arranged at intervals, and the more obvious belt artifact can be processed under the condition of not increasing the calculated amount additionally; and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed detected object. The gray values of the pixel points corresponding to the filtering units included in the filtering kernel can reflect the characteristics of the pixel points corresponding to the filtering kernel more comprehensively, so that the belt artifact pixels are determined based on the gray values of the target pixel points, and the pixel points corresponding to the detected object can be prevented from being determined as the belt artifact pixels. The belt artifact can be rapidly and accurately processed by the scheme, the imaging quality of the security inspection machine is improved, and the problem of the belt artifact under a general scene is stably solved.
The X-ray source in the security inspection device can emit X-rays, and after the detected object is placed on the upper surface of the belt, the detected object moves along with the belt and enters an area covered by the X-rays. Thus, the X-rays can pass through the object to be detected and are collected by a plurality of detectors in the detector group. The detector can determine gray values of a plurality of pixel points according to the intensity of the acquired X-ray signals. In one embodiment, the X-ray signal intensity may be determined based on the number of photons of the X-ray signal acquired by the detector.
In step S301, the electronic device may acquire image data to be processed of the security inspection device for the object to be inspected. The image data to be processed comprises gray values of a plurality of pixel points. The image data to be processed may be, for example, scan stripe data generated in the process of scanning and detecting the object by the security inspection device.
In order to determine a belt artifact pixel from a plurality of pixel points included in image data to be processed. The filter kernel may be preset before processing the belt artifact. The filter core comprises a plurality of filter units and expansion units, and the filter units and the expansion units can be arranged at intervals.
Since the belt artifact is usually represented as continuous low-gray-scale pixels, and the number of continuous pixels included in the belt artifact is far smaller than the number of continuous pixels corresponding to the object to be detected, the sliding filtering judgment manner may be adopted to determine whether each pixel in the image data to be processed is a belt artifact pixel based on the gray value of the pixel corresponding to the filtering unit in the image data to be processed, that is, step S302 is performed. The target pixel point may be a pixel point corresponding to the filtering unit in the image data to be processed.
By adopting the mode to determine the belt artifact pixels, the belt artifact pixels are determined only according to the pixel points corresponding to the filtering units in the pixel points corresponding to the filtering cores, and the belt artifact pixels are not determined according to the pixel points corresponding to the expansion units. The amount of computation required to determine the belt artifact pixels can be reduced.
Since the belt artifact will affect the display effect of the inspected object in the security inspection image, after determining the pixel points belonging to the belt artifact pixel, the electronic device may perform gray correction on the belt artifact pixel, for example, may set the gray value of the belt artifact pixel to a gray value corresponding to white, so as to generate a security inspection image corresponding to the processed inspected object, and then step S303 is performed.
The electronics can, upon determining one or more belt artifact pixels, perform a gray-scale correction on the determined belt artifact pixels. The electronic device may also perform gray-scale correction on all belt pseudo-pixels after determining all belt pseudo-pixels included in the image data to be processed. The following description is made for the two cases described above:
in one embodiment, after determining one or more belt artifact pixels, the electronic device may perform a gray-scale correction on the determined belt artifact pixels. Specifically, image data to be processed may be acquired, as well as replica data (or referred to as replica data), which is identical to the image data to be processed. After the electronic device determines the belt pseudo-image pixels from the image data to be processed, gray correction can be performed on pixel points corresponding to the belt pseudo-image pixels in the copy data. Therefore, the image data aimed at by detection and the image data aimed at by gray correction can be distinguished, and the pixel point after gray correction is prevented from affecting the accuracy of subsequent detection.
In another embodiment, after determining all of the belt artifact pixels included in the image data to be processed, the electronic device may perform gray-scale correction on all of the belt artifact pixels. Since the gradation correction is performed after all the belt pseudo-pixels are detected, the image data to which the gradation correction is performed may be image data to be processed or copy data in the above embodiment. The gradation correction may be specifically a gradation value adjustment method such as a white setting process.
In an optional embodiment, the step of performing gray-scale correction on the belt pseudo-image element to generate a security check image corresponding to the processed object to be checked may include:
after all belt pseudo-image pixels included in the image data to be processed are determined, gray level correction is carried out on each belt pseudo-image pixel, and a security inspection image corresponding to the detected object after processing is generated;
or alternatively
Obtaining duplicate data which is completely the same as the image data to be processed;
determining artifact pixels in the copied data corresponding to the belt artifact pixels in the image data to be processed based on the detected belt artifact pixels in the image data to be processed;
and carrying out gray scale correction on the pseudo-image pixels in the copied data to generate a security inspection image corresponding to the processed object to be inspected.
Therefore, in the embodiment of the present application, since the gray values of the pixel points corresponding to the plurality of filtering units included in the filtering kernel can more comprehensively reflect the characteristics of the pixel points corresponding to the filtering kernel, determining the belt artifact pixels based on the gray values of the target pixel points can avoid determining the pixel points corresponding to the object to be detected as the belt artifact pixels. The belt artifact can be rapidly and accurately processed by the scheme, the imaging quality of the security inspection machine is improved, and the problem of the belt artifact under a general scene is stably solved.
As shown in fig. 4, in the foregoing process of sliding the preset filter kernel, the step of determining whether each pixel point in the image data to be processed is a belt artifact pixel based on the gray value of the target pixel point in the image data to be processed may include:
s401, sliding a preset filter kernel with a fixed step length according to the storage sequence of the image data to be processed in a memory;
because adjacent pixel points in the image data to be processed are continuously stored, in order to determine belt artifact pixels in the image data to be processed, the electronic device can slide the preset filter kernel in a fixed step length according to the storage sequence of the image data to be processed in the memory. Wherein the fixed step size may be one pixel.
S402, sliding the preset filter kernel once, and determining whether the central target pixel point is a belt artifact pixel according to the relation between the central target pixel point and the edge target pixel point in the image data to be processed and preset threshold conditions and the number of other target pixel points meeting the preset threshold conditions;
the center target pixel point is a pixel point corresponding to a center filter unit of the preset filter core, the edge target pixel point is a pixel point corresponding to an edge filter unit of the preset filter core, and the other target pixel points are pixel points corresponding to filter units except the center filter unit and the edge filter unit.
The embodiment of the application further provides a filter kernel not including the expansion unit, and a mode of detecting the belt artifact pixels by adopting the filter kernel not including the expansion unit will be described below:
in this case, the filter kernel consists of successive filter elements. The filter kernel may be preset prior to identifying the belt artifact pixels. In particular, since the filter kernel includes only filter units, it is only necessary to set the number of filter units, i.e., the length of the filter kernel.
The number of filtering units may be set according to the length of the belt artifact to be detected. Since the belt artifact pixels generally occupy a plurality of continuous pixel points, if the length of the filter kernel is equal to the length of the belt artifact to be detected, the electronic device cannot determine whether other continuous pixel points exist on two sides of the pixel point corresponding to the filter kernel, and further may misjudge the pixel point corresponding to the detected object as the belt artifact pixel, so that the length of the filter kernel should be at least greater than the length of the belt artifact to be detected.
After the filter kernel is set, the electronic device can slide the filter kernel with a fixed step length according to the storage sequence of the image data to be processed in the memory. The electronic device can determine whether the central pixel point is a belt artifact pixel according to the relation between the gray value of the central pixel point corresponding to the central filtering unit and the preset threshold condition and the number of the pixel points corresponding to all the filtering units meeting the preset threshold condition after sliding the filtering core once. The preset threshold condition may be less than a preset gray value threshold.
Specifically, under the condition that the central pixel point belongs to the belt artifact pixel or the detected object pixel, the central pixel point meets the preset threshold condition, so that the electronic equipment can judge whether the gray value of the central pixel point is smaller than the preset gray value threshold. If the gray value of the central pixel point is smaller than the preset gray value threshold, the pixel points corresponding to the filtering kernel are possibly the pixel points corresponding to the belt artifact or the pixel points corresponding to the detected object.
In order to determine whether the plurality of pixel points are pixel points corresponding to the belt artifact, the electronic device may determine whether the number of pixel points corresponding to the gray value smaller than the preset gray value threshold is not greater than the preset number when the gray value of the central pixel point is smaller than the preset gray value threshold. The preset number may be equal to the maximum number of pixels included in the belt artifact to be detected. For example, if the belt artifact to be detected includes 1 pixel to 3 pixels, the preset number may be 3; if the belt artifact to be detected comprises 1 pixel-5 pixels, the preset number may be 5.
If the number of corresponding pixels having a gray value less than the preset gray value threshold is not greater than the preset number, the center pixel may be determined to be a belt artifact pixel.
Typically, the belt artifact occupies 1 pixel-6 pixels in succession. For example, if the belt artifact to be detected includes 1 pixel to 3 pixels, the filter kernel may be set to include five filter units, each of which has a size equal to that of one pixel.
In this case, a schematic diagram of detecting belt artifacts including 3 or less pixels may be as shown in fig. 5. The following will be described with reference to fig. 5, for the case where the belt artifact is one pixel, two pixels, and three pixels, respectively:
for single-pixel belt artifact or shot noise, only one condition exists, namely a pixel point corresponding to a central filtering unit of a filtering core is a single pixel point included by the belt artifact, namely condition 1, so that the belt artifact pixel can be detected.
For the two-pixel belt artifact, two situations exist, namely the belt artifact pixel can be detected, namely the pixel point corresponding to the central filtering unit of the filtering core is one pixel point included in the belt artifact pixel, and the number of the pixel points smaller than the preset gray value threshold is two, namely the situation 1 and the situation 2.
For the three-pixel belt artifact, three situations exist, namely the belt artifact pixel can be detected, namely the pixel point corresponding to the central filtering unit of the filtering core is one pixel point included in the belt artifact pixel, and the number of the pixel points smaller than the preset gray value threshold is three, namely the situations 1-3.
According to the thought of adopting the continuous filtering unit to detect the belt artifact pixels, the quantity of the filtering units on two sides of the central filtering unit of the limiting filtering core is equal, and the sum of the quantity of the central filtering unit and the quantity of the filtering units on one side of the central filtering unit is equal to the maximum length of the belt artifact pixels to be detected. In this way, it is possible to derive that the number of filter units included in the filter kernel is singular, and that in the case where the maximum number of pixel points included in the belt artifact pixels to be detected is n, the length of the filter kernel, that is, the number of filter units included in the filter kernel l=2× (n// 2+1) +1.
In the case where the filter kernel does not include the expansion unit, since the filter unit in the filter kernel is continuous and the belt artifact pixels are usually 6 continuous pixel points, the longer the filter kernel length, the more subject pixels are eliminated. Moreover, since the filter kernel only includes the filter unit, it is necessary to determine whether all pixel points corresponding to the filter kernel satisfy a preset threshold condition, and the calculation amount is large.
In order to solve the problems that the pixels of the object are eliminated and the calculation amount is large, the embodiment of the application provides a filter core including an expansion unit.
In this case, the filter kernel includes a center filter unit, an edge filter unit, other filter units, and an expansion unit. Expansion units are arranged between the central filtering unit and the adjacent non-central filtering unit, between other filtering units and the adjacent edge filtering units and between the adjacent other filtering units. Wherein the other filtering units are filtering units except the center filtering unit and the edge filtering unit.
For example, the order of the respective filter units and the expansion units in the filter core may be: the device comprises an edge filtering unit, an expansion unit, other filtering units, an expansion unit, a central filtering unit, an expansion unit, other filtering units, an expansion unit and an edge filtering unit; the method can also be as follows: edge filter unit, expansion unit, other filter unit, expansion unit, center filter unit, expansion unit, other filter unit, expansion unit, edge filter unit. This is reasonable.
The schematic diagram of the filter core including the expansion unit provided in this embodiment of the present application may be as shown in fig. 6, where the unit corresponding to P3 is a central filter unit, the units corresponding to D1-D4 are expansion units, the units corresponding to P2 and P4 are other filter units except the central filter unit and the edge filter unit, and the units corresponding to P1 and P5 are edge filter units.
And under the condition that a central target pixel point corresponding to a central filtering unit of the preset filtering core is a belt artifact pixel, the central target pixel point accords with a preset threshold condition, an edge target pixel point corresponding to an edge filtering unit of the preset filtering core does not meet the preset threshold condition, and the number of the other target pixel points corresponding to the filtering units except the central filtering unit and the edge filtering unit, which meet the preset threshold condition, is not greater than the preset number.
Based on the condition that the central target pixel point is the belt artifact pixel, the central target pixel point, the edge target pixel point and other target pixel points correspond to conditions. In step S402, the electronic device may determine whether the center target pixel point is a belt artifact pixel according to the relationship between the center target pixel point and the edge target pixel point in the image data to be processed and the preset threshold condition, and the number of other target pixel points satisfying the preset threshold condition, when the preset filter kernel is slid once.
As can be seen, in the embodiment of the present application, the electronic device slides the preset filter kernel with a fixed step according to the storage sequence of the image data to be processed in the memory; each time the preset filter kernel is slid, determining whether the center target pixel point is a belt artifact pixel or not according to the relation between the center target pixel point and the edge target pixel point in the image data to be processed and preset threshold conditions respectively and the number of other target pixel points meeting the preset threshold conditions; the central target pixel point is a pixel point corresponding to a central filtering unit of a preset filtering core, the edge target pixel point is a pixel point corresponding to an edge filtering unit of the preset filtering core, and other target pixel points are pixel points corresponding to filtering units except the central filtering unit and the edge filtering unit. Because the central target pixel point corresponding to the central filtering unit of the preset filtering core accords with the preset threshold condition when the central target pixel point is the belt artifact pixel, the edge target pixel point corresponding to the edge filtering unit of the preset filtering core does not meet the preset threshold condition, and the number of the other target pixel points corresponding to the filtering units except the central filtering unit and the edge filtering unit does not meet the preset threshold condition is not larger than the preset number. Therefore, the electronic device can determine whether the central target pixel point is the belt artifact pixel based on the conditions corresponding to the central target pixel point, the edge target pixel point and other target pixel points. In this way, the belt artifact pixels can be determined quickly and accurately, and determination of the object pixels as belt artifact pixels can be avoided. Meanwhile, the debugging standard and pressure of the conveying belt module of the security inspection equipment can be reduced. And the filtering sliding window direction is consistent with the storage direction of the image data in the memory, so that the cache hit rate of the CPU can be ensured, and the processing speed is far faster than that of the conventional algorithm for processing the common morphological image. In the embodiment of the present application, the threshold values involved may be set reasonably according to statistical experience or technical requirements.
As an implementation manner of the embodiment of the present application, as shown in fig. 7, the step of determining whether the center target pixel point is a belt artifact pixel according to the relationship between the center target pixel point and the edge target pixel point in the image data to be processed and the preset threshold condition, and the number of other target pixel points satisfying the preset threshold condition may include:
s701, judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value; if the gray value of the center target pixel point is smaller than the preset gray value threshold, executing step S702;
under the condition that the gray value of the central target pixel point is smaller than a preset gray value threshold value, a plurality of pixel points corresponding to the preset filter kernel may be belt artifact pixels or detected object pixels. Accordingly, the electronic device may determine whether the gray value of the center target pixel point is less than a preset gray value threshold. In the case that the gray value of the center target pixel point is smaller than the preset gray value threshold, in order to further determine whether the plurality of pixel points corresponding to the preset filter kernel are belt artifact pixels, the electronic device may execute step S702.
The preset gray value threshold may be determined according to any manner for determining a threshold, such as a global threshold, an Otus (Otus) threshold, an iterative threshold, and the like.
In one embodiment, the preset gray value threshold may be determined based on a global threshold. Specifically, the electronic device may determine a gray histogram according to gray values corresponding to all pixel points included in the image data to be processed, and further determine a preset gray value threshold according to the gray histogram.
For example, a schematic diagram of determining belt artifact pixels based on the preset filter kernel shown in fig. 6 may be as shown in fig. 8. The maximum number of pixels of the belt artifact pixels to be detected is 4, that is to say, in this case, consecutive 1 pixel-4 pixel points will be determined as belt artifact pixels.
The preset filter kernel slides along the direction indicated by the arrow in fig. 8 with the side length of the unit pixel point as the step length. If the length of the belt artifact is 4 pixels, the preset filter kernel is subjected to 4 slides, and the conditions of the corresponding pixel points in the image data to be processed after each slide are respectively 1-4.
As can be seen from fig. 8, in cases 1 to 4, the center target pixel is smaller than the preset gray value threshold. Step S702 may continue to be performed for cases 1-4.
S702, determining whether the gray value of the other target pixel points is smaller than the preset gray value threshold; if the gray value of the other target pixel point is smaller than the preset gray value threshold, step S703 is executed;
because the belt artifact pixels are usually a plurality of continuous pixels, after determining that the gray value of the central target pixel is less than the preset gray value threshold, the electronic device may determine whether the gray values of other target pixels are less than the preset gray value threshold.
If the gray value of the other target pixel points is smaller than the preset gray value threshold, the central target pixel point is possibly a belt artifact pixel. For further determination, the electronic device may perform step S703.
In the example of the receiving step S701, for each of cases 1 to 4, there are pixels corresponding to P4, pixels corresponding to P2, and pixels corresponding to P2, where the gray value of the other target pixel is smaller than the preset gray value threshold. Thus, for cases 1-4, step S703 may continue to be performed.
S703, determining whether the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not greater than the preset number; if the number of the target pixel points corresponding to the gray value smaller than the preset gray value threshold is not greater than the preset number, step S704 is executed;
Since the number of pixels of the belt artifact is generally much smaller than the number of pixels of the object, the electronic device may determine whether the number of target pixel points corresponding to the gray value smaller than the preset gray value threshold is not greater than the preset number. If the number of the target pixels whose corresponding gray values are smaller than the preset gray value threshold is not greater than the preset number, which indicates that the center target pixel may be a belt pseudo-image pixel, step S704 may be continued.
The preset number may be determined according to the length of the belt artifact to be detected, the number of other filtering units, and the length of the expansion unit in the preset filtering core.
In the example of the adapting step S702, if the preset number is 2, the target pixels smaller than the preset gray value threshold in case 1 are the pixels corresponding to P3 and the pixels corresponding to P4, respectively; the target pixel points smaller than the preset gray value threshold in the case 2 are respectively a pixel point corresponding to P3 and a pixel point corresponding to P4; the target pixel points smaller than the preset gray value threshold in the case 3 are respectively a pixel point corresponding to P2 and a pixel point corresponding to P3; in case 4, the target pixel points smaller than the preset gray value threshold are the pixel point corresponding to P2 and the pixel point corresponding to P3 respectively.
Since in cases 1-4, the number of target pixels whose corresponding gray values are smaller than the preset gray value threshold is not greater than the preset number. Thus, for cases 1-4, step S704 may continue to be performed.
S704, determining whether the gray value of the edge target pixel point is larger than the preset gray value threshold; if the gray value of the edge target pixel point is greater than the preset gray value threshold, executing step S705;
in the preset filter kernel, the lengths of the filter unit and the expansion unit at each side of the central filter unit are usually not smaller than the length of the belt artifact, so that the belt artifact in the image data to be processed cannot simultaneously meet the condition that the gray value of the central target pixel point is smaller than a preset gray value threshold value and the gray value of the edge target pixel point is smaller than a preset gray value threshold value.
The electronic device may determine whether a gray value of the edge target pixel point is greater than a preset gray value threshold. And if the gray value of the edge target pixel point is larger than a preset gray value threshold value, indicating that the center target pixel point is a belt artifact pixel. And if the gray value of the edge target pixel point is smaller than the preset gray value threshold value, indicating that the center target pixel point is the pixel of the detected object.
In the example of the adapting step S703, in the cases 1 to 4, since the gray values of the edge target pixel points are all greater than the preset gray value threshold, it can be determined that the center target pixel points corresponding to the cases 1 to 4 are all the belt artifact pixels.
And S705, determining the central target pixel point as a belt artifact pixel.
When the gray value of the edge target pixel point is larger than the preset gray value threshold, the fact that the pixel points corresponding to the preset filter kernel are belt artifacts is indicated, and the electronic equipment can determine that the center target pixel point is the belt artifact pixel.
As an implementation manner, the condition that the pixel point in the image data to be processed meets the preset threshold condition may be represented by a preset function, where an argument of the preset function is a position identifier of the filtering unit in the preset filtering core and an identifier of the pixel point in the image data to be processed corresponding to the filtering unit. If the pixel point meets the preset threshold condition, the function value of the preset function is 1; otherwise, the function value of the preset function is 0.
Therefore, the relation between the pixel points and the preset threshold condition can be converted into addition operation, and whether the gray value of the pixel points meets the preset threshold condition and the number of the corresponding pixel points meeting the preset threshold condition can be rapidly and accurately determined.
Taking the preset filter kernel and the data unit to be processed as shown in fig. 8 as an example, the preset threshold condition is that the gray value corresponding to the pixel point is smaller than the preset gray value threshold.
The gray value of the central target pixel point corresponding to P3 is smaller than the preset gray value threshold, which can be expressed as: f (P3, cali) n ) =1. Wherein P3 is the position identification of a filtering unit in a preset filtering core, cali n The gray value of the center target pixel point corresponding to P3.
Among the target pixel points corresponding to P2-P3, the number of target pixel points smaller than the preset gray value threshold is not greater than the preset number 2, and may be expressed as: f (P3, cali) n )+F(P2,Cali n-D2 )+F(P4,Cali n+D2 ) And is less than or equal to 2. Wherein Cali n-D2 The gray value of the target pixel corresponding to P2 is represented. Cali n+D2 The gray value of the target pixel corresponding to P4 is represented.
The gray value of the edge target pixel point corresponding to each of P1 and P5 is greater than the preset gray value threshold, which can be expressed as: f (P1, cali) n-D1-D1 )+F(P5,Cali n+D1+D2 ) =0. Wherein Cali n-D1-D2 Representing the gray value, cali, of the edge target pixel point corresponding to P1 n+D1+D2 And representing the gray value of the edge target pixel point corresponding to the P5.
In the embodiment of the application, the electronic device may determine whether the gray value of the central target pixel point is smaller than a preset gray value threshold; if the gray value of the central target pixel point is smaller than a preset gray value threshold, determining whether the gray values of other target pixel points are smaller than the preset gray value threshold; determining whether the number of the corresponding target pixel points with the gray values smaller than a preset gray value threshold is not larger than a preset number; if the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than the preset number, determining whether the gray value of the edge target pixel points is larger than the preset gray value threshold; and if the gray value of the edge target pixel point is larger than a preset gray value threshold value, determining the center target pixel point as a belt artifact pixel. The electronic device may determine whether the gray value of the center target pixel point is smaller than a preset gray value threshold, and further determine whether a pixel point corresponding to the preset filter kernel may be a belt artifact. Since the belt artifact is usually a plurality of continuous pixels and the number of pixels of the belt artifact is small, the electronic device may further determine whether the number of target pixels having a corresponding gray value smaller than the preset gray value threshold is greater than the preset number and whether the gray value of the edge target pixel is greater than the preset gray value threshold in case that the gray value of the center target pixel is smaller than the preset gray value threshold, so as to determine the number of continuous target pixels. Because the number of the continuous pixel points included in the detected object is usually far greater than that of the continuous pixel points included in the belt artifact, the electronic equipment can rapidly and accurately determine the belt artifact pixels and the background noise, the detected object pixels cannot be misjudged as the belt artifact pixels, and the processing effect of the belt artifact can be improved.
As an implementation manner of the embodiment of the present application, the number of the plurality of filtering units included in the preset filtering kernel and the length of the expansion unit are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering kernel is greater than the length of the belt artifact to be detected.
In order that the preset filter kernel may detect complete belt artifacts, the receptive field length of the preset filter kernel may be greater than the length of the belt artifact to be detected. If the lengths of the belt artifacts to be detected are different, the length of the expansion unit and the number of filter units may be set according to the lengths of the belt artifacts to be detected. The receptive field length of the filter core is preset, that is, the actual total length of the filter core (the total length of all filter units and expansion units) is preset.
In other words, in the embodiment of the present application, the actual total length of the preset filter kernel is greater than the length of the belt artifact to be detected, and the filter units on two sides of the central filter unit are symmetrically arranged, where the length of each filter unit corresponds to one pixel unit, the length of each expansion unit is reasonably determined according to the number of filter units and the actual total length of the preset filter kernel, and the expansion units are used to increase the receptive field length of the filter kernel, and do not actually participate in calculation; further alternatively, the distance between other filter units further from the center filter unit may be greater than or equal to the length of the belt artifact to be detected, in addition to the edge filter units on both sides of the center filter unit. As shown in fig. 6, taking an example in which the preset filter kernel includes 5 filter units and 4 expansion units, the length between the filter units P2 and P4 located at both sides of the central filter unit P3 may be equal to or greater than the length of the belt artifact to be detected, except that it is required that the actual total length of the preset filter kernel is greater than the length of the belt artifact to be detected.
In the embodiment of the present application, the more the number of filter units in the preset filter kernel is, that is, the more the number of pixels involved in calculation is, the consumption calculation amount is increased, so the number of filter units in the preset filter kernel can be set to be 5, and the effect of both the filter calculation amount and the artifact detection is achieved.
For example, the belt artifact to be detected is 1 pixel to 6 pixels in length. Two preset filter kernels that can be applied to detect the above-described belt artifact are provided below, as shown in fig. 9 (a) and 9 (b), respectively.
Fig. 9 (a) is a schematic diagram of a preset filter kernel for detecting belt artifacts at 6 pixels. The number of the filtering units is 5, and the filtering units are P1-P5 respectively. Wherein, P3 is a central filtering unit, P2 and P4 are other filtering units, and P1 and P5 are edge filtering units. The number of expansion units is 4, D1-D4 respectively, and the length is 2 pixels.
In this case, the electronic device may determine whether the gray value of the center target pixel point is smaller than a preset gray value threshold; if the gray value of the central target pixel point is smaller than the preset gray value threshold, determining whether the gray values of other target pixel points are smaller than the preset gray value threshold. Further, it is determined whether the number of target pixel points corresponding to the gray value smaller than the preset gray value threshold is not greater than 2. And if the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than 2, determining whether the gray value of the edge target pixel points is larger than the preset gray value threshold. And if the gray value of the edge target pixel point is larger than a preset gray value threshold value, determining the center target pixel point as a belt artifact pixel. Case 1-case 6 are cases where the 6 belt artifacts include 6 pixel points, for which 6 cases the electronic device may determine the center target pixel point as the belt artifact pixel based on the above-described procedure.
Fig. 9 (b) is a schematic diagram of another preset filter kernel for detecting 6-pixel belt artifacts. The number of the filtering units is 7, and the filtering units are P1-P7 respectively. Wherein, P4 is a central filtering unit, P2, P3, P5 and P6 are other filtering units, and P1 and P7 are edge filtering units. The number of expansion units is 6, D1-D6 respectively, and the length is 1 pixel.
In this case, the electronic device may determine whether the gray value of the center target pixel point is smaller than a preset gray value threshold; if the gray value of the central target pixel point is smaller than the preset gray value threshold, determining whether the gray values of other target pixel points are smaller than the preset gray value threshold. Further, it is determined whether the number of target pixel points corresponding to the gray value smaller than the preset gray value threshold is not greater than 3. And if the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than 3, determining whether the gray value of the edge target pixel points is larger than the preset gray value threshold. And if the gray value of the edge target pixel point is larger than a preset gray value threshold value, determining the center target pixel point as a belt artifact pixel. Case 1-case 6 are cases where the 6 belt artifacts include 6 pixel points, for which 6 cases the electronic device may determine the center target pixel point as the belt artifact pixel based on the above-described procedure.
Among the above two preset filter kernels for detecting belt artifacts of 6 pixels, since the number of filter units included in the preset filter kernel shown in fig. 9 (a) is small, the processing speed can be increased by adopting the preset filter kernel shown in fig. 9 (a) compared to the preset filter kernel shown in fig. 9 (b).
It can be seen that, in this embodiment of the present application, the number of the plurality of filtering units and the length of the expansion unit that may be included in the preset filtering core are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering core is greater than the length of the belt artifact to be detected. The number of the filtering units and the length of the expansion units can be adjusted according to the length of the belt artifact to be detected and the detection time consumption requirement, so that the preset filtering core has strong generalization capability, and the belt artifact pixels can be rapidly and accurately determined.
As an implementation manner of the embodiment of the present application, the number of the plurality of filtering units included in the preset filtering core may be 5, and the preset number may be 2.
In the case where the number of filter units is 5, the filter units include 1 center filter unit, 2 other filter units, and 2 edge filter units. In this way, the length of the expansion unit can be changed for detecting belt artifacts of different lengths, depending on the length of the belt artifact to be detected.
In the step of determining whether the number of the target pixel points whose corresponding gray values are smaller than the preset gray value threshold is not greater than the preset number in the case that the number of the filtering units is 5, the preset number may be 2. Therefore, under the condition that the gray value of the central target pixel point is smaller than the preset gray value threshold, the condition that whether the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than the preset number can be met only by the fact that the gray values of 1 other target pixel points are smaller than the preset gray value threshold.
It can be seen that, in the embodiment of the present application, the number of the plurality of filtering units included in the preset filtering core is 5, and the preset number is 2. Since the number of filter units is small, the calculation amount can be reduced, and the belt artifact pixels can be determined quickly. Meanwhile, the imaging quality of the security inspection machine is improved, and the problem of belt artifact in a general scene is stably solved.
As an implementation manner of the embodiment of the present application, the step of acquiring image data to be processed of the security inspection device for the object to be inspected may include:
the electronic equipment can acquire the bright field template and the dark field template of the security inspection equipment and the image data to be processed of the inspected object.
The bright field template is the X-ray signal intensity collected by the detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is static, the dark field template is the X-ray signal intensity collected by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is static, and the X-ray signal intensity collected by the detector under the condition that the image data to be processed of the object to be inspected is opened and the X-ray source is overstocked. For example, the preset time period may be 20ms to 40ms.
The electronic device can calculate the gray value Cali of the pixel point according to the following formula based on the bright field template, the dark field template and the image data to be processed n :
R n =Air n -Bk n
Wherein, air n Bk is bright field template data n Scan as dark field template data n To be processed image data Bk n For dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor. The bright field correction parameter is an average value of X-ray signals emitted by the ray source captured by the detector in a preset time period under the condition that the ray source is opened and not packed.
The correction scaling factor may be determined based on the maximum quantization depth of an ADC (Analog to Digital Converter, analog-to-digital converter) of the detector in the security device. For example, if the detector in the security device is 16 bits, then the correction scaling factor may be 65535.
In the above embodiment, the electronic device may set the determined gray value of the belt artifact pixel to the above correction scaling factor. For example, cali n For the gray value of the pixel point corresponding to the belt pseudo-image pixel, the electronic device can enable Cali to n And (2) performing gray correction on the pixel points corresponding to the belt pseudo-image pixels.
In the embodiment of the application, the electronic device can acquire the bright field template and the dark field template of the security inspection device and the image data to be processed of the inspected object; based on the bright field template, the dark field template and the image data to be processed, calculating the gray value Cali of the pixel point according to the following formula n :R n =Air n -Bk n ,Wherein, air n Bk is bright field template data n Scan as dark field template data n To be processed image data Bk n For dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor. Therefore, the electronic equipment can accurately calculate the gray value corresponding to each pixel point, and further the accuracy of belt artifact processing is improved.
By applying the belt artifact processing method provided by the embodiment of the application, the generated security inspection image corresponding to the detected object can be shown as shown in fig. 10. As can be seen by comparison with fig. 2, there is no background noise and no belt artifact in fig. 10.
In the technical scheme of the application, the related operations of acquiring, storing, using, processing, transmitting, providing, disclosing and the like of the user personal information are all performed under the condition of obtaining the authorization of the user.
Corresponding to the above method for processing belt artifact, the embodiment of the present application further provides a device for processing belt artifact, and the following description describes the device for processing belt artifact provided in the embodiment of the present application.
As shown in fig. 11, a belt artifact processing apparatus, the apparatus comprising:
a data acquisition module 1101, configured to acquire image data to be processed of a security inspection device for an object to be inspected;
the pixel determining module 1102 is configured to determine, in a sliding process of a preset filter kernel, whether each pixel point in the image data to be processed is a belt artifact pixel based on a gray value of a target pixel point in the image data to be processed, where the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, and the preset filter kernel further includes an expansion unit, where the filter unit is set at intervals with the expansion unit;
the gray level correction module 1103 is configured to perform gray level correction on the belt pseudo-image element, and generate a processed security check image corresponding to the object to be checked.
In the embodiment of the application, the electronic device may acquire the image data to be processed of the security inspection device for the inspected object; in the sliding process of the preset filter kernel, based on the gray value of a target pixel point in the image data to be processed, determining whether each pixel point in the image data to be processed is a belt artifact pixel, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, the filter units and the expansion unit are arranged at intervals, and the more obvious belt artifact can be processed under the condition of not increasing the calculated amount additionally; and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed detected object. The gray values of the pixel points corresponding to the filtering units included in the filtering kernel can reflect the characteristics of the pixel points corresponding to the filtering kernel more comprehensively, so that the belt artifact pixels are determined based on the gray values of the target pixel points, and the pixel points corresponding to the detected object can be prevented from being determined as the belt artifact pixels. The belt artifact can be rapidly and accurately processed by the scheme, the imaging quality of the security inspection machine is improved, and the problem of the belt artifact under a general scene is stably solved.
As an implementation manner of the embodiment of the present application, the above pixel determining module 1102 may include:
the filtering core sliding sub-module is used for sliding a preset filtering core in a fixed step length according to the storage sequence of the image data to be processed in the memory;
the pixel determining submodule is used for determining whether the central target pixel point is a belt artifact pixel or not according to the relation between the central target pixel point and the edge target pixel point in the image data to be processed and a preset threshold condition respectively and the number of other target pixel points meeting the preset threshold condition once sliding the preset filter kernel;
the center target pixel point is a pixel point corresponding to a center filter unit of the preset filter core, the edge target pixel point is a pixel point corresponding to an edge filter unit of the preset filter core, and the other target pixel points are pixel points corresponding to filter units except the center filter unit and the edge filter unit.
As an implementation manner of the embodiment of the present application, the pixel determining sub-module may include:
the central target pixel point judging unit is used for judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value or not;
The other target pixel point judging unit is used for determining whether the gray value of the other target pixel points is smaller than a preset gray value threshold value or not if the gray value of the central target pixel point is smaller than the preset gray value threshold value;
a number determining unit configured to determine, if the gray value of the other target pixel point is smaller than the preset gray value threshold, whether the number of target pixel points whose corresponding gray values are smaller than the preset gray value threshold is not greater than a preset number;
an edge target pixel point judging unit, configured to determine whether a gray value of the edge target pixel point is greater than the preset gray value threshold if the number of target pixel points corresponding to the gray value being less than the preset gray value threshold is not greater than the preset number;
and the pixel determining unit is used for determining that the central target pixel point is a belt artifact pixel if the gray value of the edge target pixel point is larger than the preset gray value threshold value.
As an implementation manner of the embodiment of the present application, the number of the plurality of filtering units included in the preset filtering kernel and the length of the expansion unit are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering kernel is greater than the length of the belt artifact to be detected.
As an implementation manner of the embodiment of the present application, the number of the plurality of filtering units included in the preset filtering core is 5, and the preset number is 2.
As an implementation manner of the embodiment of the present application, the data obtaining module 1101 may include:
the data acquisition sub-module is used for acquiring a bright field template, a dark field template and image data to be processed of an object to be detected of the security inspection equipment, wherein the bright field template is the X-ray signal intensity acquired by a detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is stationary, and the dark field template is the X-ray signal intensity acquired by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is stationary;
a gray value calculation sub-module for calculating gray values Cali of the pixel points according to the following formula based on the bright field template, the dark field template and the image data to be processed n :
R n =Air n -Bk n
Wherein, air n Bk for the bright field template data n Scan for the dark field template data n Bk for the image data to be processed n For the dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor.
In one embodiment, the gray-scale correction module 1103 is configured to perform gray-scale correction on each belt pseudo-image element after determining all belt pseudo-image elements included in the image data to be processed, so as to generate a security check map corresponding to the processed object to be checked; alternatively, the gray-scale correction module 1103 is configured to: obtaining duplicate data which is completely the same as the image data to be processed; determining artifact pixels in the copied data corresponding to the belt artifact pixels in the image data to be processed based on the detected belt artifact pixels in the image data to be processed; and carrying out gray scale correction on the pseudo-image pixels in the copied data to generate a security inspection image corresponding to the processed object to be inspected.
The embodiment of the application also provides an electronic device, as shown in fig. 12, including:
a memory 1201 for storing a computer program;
the processor 1202 is configured to implement the steps of the method for processing belt artifact according to any of the above embodiments when executing the program stored in the memory 1201.
And the electronic device may further comprise a communication bus and/or a communication interface, through which the processor 1202, the communication interface, and the memory 1201 communicate with each other.
In the embodiment of the application, the electronic device may acquire the image data to be processed of the security inspection device for the inspected object; in the sliding process of the preset filter kernel, based on the gray value of a target pixel point in the image data to be processed, determining whether each pixel point in the image data to be processed is a belt artifact pixel, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, the filter units and the expansion unit are arranged at intervals, and the more obvious belt artifact can be processed under the condition of not increasing the calculated amount additionally; and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed detected object. The gray values of the pixel points corresponding to the filtering units included in the filtering kernel can reflect the characteristics of the pixel points corresponding to the filtering kernel more comprehensively, so that the belt artifact pixels are determined based on the gray values of the target pixel points, and the pixel points corresponding to the detected object can be prevented from being determined as the belt artifact pixels. The belt artifact can be rapidly and accurately processed by the scheme, the imaging quality of the security inspection machine is improved, and the problem of the belt artifact under a general scene is stably solved.
The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In yet another embodiment provided herein, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of the method of treating any of the above-mentioned belt artifacts.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform the method of processing belt artifacts of any of the above embodiments.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a Solid State Disk (SSD), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, the electronic device, the computer-readable storage medium, and the computer program product, the description is relatively simple, as it is substantially similar to the method embodiments, and relevant points are found in the partial description of the method embodiments.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modifications, equivalent substitutions, improvements, etc. that are within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (11)
1. A method of treating belt artifacts, the method comprising:
acquiring image data to be processed of security inspection equipment aiming at an inspected object;
in a preset filtering kernel sliding process, determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on a gray value of a target pixel point in the image data to be processed, wherein the target pixel point is a pixel point corresponding to a plurality of filtering units included in the preset filtering kernel in the image data to be processed, the preset filtering kernel further comprises an expansion unit, and the filtering units and the expansion unit are arranged at intervals;
and carrying out gray level correction on the belt pseudo-image pixels to generate a security inspection image corresponding to the processed object to be inspected.
2. The method according to claim 1, wherein the step of determining whether each pixel point in the image data to be processed is a belt artifact pixel based on a gray value of a target pixel point in the image data to be processed in a preset filter kernel sliding process includes:
Sliding a preset filter kernel with a fixed step length according to the storage sequence of the image data to be processed in the memory;
each time the preset filter kernel is slid, determining whether the center target pixel point is a belt artifact pixel according to the relation between the center target pixel point and the edge target pixel point in the image data to be processed and a preset threshold condition respectively and the number of other target pixel points meeting the preset threshold condition;
the center target pixel point is a pixel point corresponding to a center filter unit of the preset filter core, the edge target pixel point is a pixel point corresponding to an edge filter unit of the preset filter core, and the other target pixel points are pixel points corresponding to filter units except the center filter unit and the edge filter unit.
3. The method according to claim 2, wherein the step of determining whether the center target pixel point is a belt artifact pixel according to a relationship between a center target pixel point and an edge target pixel point in the image data to be processed and a preset threshold condition, respectively, and the number of other target pixel points satisfying the preset threshold condition, includes:
Judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value or not;
if the gray value of the central target pixel point is smaller than the preset gray value threshold, determining whether the gray values of the other target pixel points are smaller than the preset gray value threshold;
if the gray value of the other target pixel points is smaller than the preset gray value threshold, determining whether the number of the target pixel points with the corresponding gray values smaller than the preset gray value threshold is not larger than a preset number;
if the number of the corresponding target pixel points with the gray values smaller than the preset gray value threshold is not larger than the preset number, determining whether the gray value of the edge target pixel points is larger than the preset gray value threshold;
and if the gray value of the edge target pixel point is larger than the preset gray value threshold, determining that the center target pixel point is a belt artifact pixel.
4. A method according to any of claims 1-3, characterized in that the number of filter units comprised by the preset filter kernel and the length of the expansion unit are determined based on the length of the belt artifact to be detected, the receptive field length of the preset filter kernel being larger than the length of the belt artifact to be detected.
5. A method according to claim 3, wherein the preset filter kernel comprises a number of filter units of 5 and the preset number of filter units is 2.
6. A method according to any one of claims 1-3, wherein the step of acquiring image data to be processed of the security inspection device for the inspected object comprises:
acquiring a bright field template, a dark field template and image data to be processed of an inspected object of security inspection equipment, wherein the bright field template is the X-ray signal intensity acquired by a detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is stationary, and the dark field template is the X-ray signal intensity acquired by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is stationary;
based on the bright field template, the dark field template and the image data to be processed, calculating a gray value Cali of the pixel point according to the following formula n :
R n =Air n -Bk n
Wherein, air n Bk for the bright field template data n Scan for the dark field template data n Bk for the image data to be processed n For the dark field template data, R n For the bright field correction parameter, factor is the correction scaling Factor.
7. The method of claim 1, wherein the step of performing gray scale correction on the belt artifact pixels to generate a processed security inspection image corresponding to the inspected object comprises:
After all belt pseudo-image pixels included in the image data to be processed are determined, gray level correction is carried out on each belt pseudo-image pixel, and a security inspection image corresponding to the detected object after processing is generated;
or alternatively
Obtaining duplicate data which is completely the same as the image data to be processed;
determining artifact pixels in the copied data corresponding to the belt artifact pixels in the image data to be processed based on the detected belt artifact pixels in the image data to be processed;
and carrying out gray scale correction on the pseudo-image pixels in the copied data to generate a security inspection image corresponding to the processed object to be inspected.
8. A belt artifact handling apparatus, the apparatus comprising:
the data acquisition module is used for acquiring image data to be processed of the security inspection equipment aiming at the inspected object;
the pixel determining module is used for determining whether each pixel point in the image data to be processed is a belt artifact pixel or not based on a gray value of a target pixel point in the image data to be processed in a preset filter kernel sliding process, wherein the target pixel point is a pixel point corresponding to a plurality of filter units included in the preset filter kernel in the image data to be processed, the preset filter kernel further comprises an expansion unit, and the filter units and the expansion unit are arranged at intervals;
And the gray level correction module is used for carrying out gray level correction on the belt pseudo-image pixels and generating a processed security check image corresponding to the detected object.
9. The apparatus of claim 8, wherein the pixel determination module comprises:
the filtering core sliding sub-module is used for sliding a preset filtering core in a fixed step length according to the storage sequence of the image data to be processed in the memory;
the pixel determining submodule is used for determining whether the central target pixel point is a belt artifact pixel or not according to the relation between the central target pixel point and the edge target pixel point in the image data to be processed and a preset threshold condition respectively and the number of other target pixel points meeting the preset threshold condition once sliding the preset filter kernel;
the central target pixel point is a pixel point corresponding to a central filtering unit of the preset filtering core, the edge target pixel point is a pixel point corresponding to an edge filtering unit of the preset filtering core, and the other target pixel points are pixel points corresponding to filtering units except the central filtering unit and the edge filtering unit;
The pixel determination submodule includes:
the central target pixel point judging unit is used for judging whether the gray value of the central target pixel point is smaller than a preset gray value threshold value or not;
the other target pixel point judging unit is used for determining whether the gray value of the other target pixel points is smaller than the preset gray value threshold value or not if the gray value of the central target pixel point is smaller than the preset gray value threshold value;
a number determining unit configured to determine, if the gray value of the other target pixel point is smaller than the preset gray value threshold, whether the number of target pixel points whose corresponding gray values are smaller than the preset gray value threshold is not greater than a preset number;
an edge target pixel point judging unit, configured to determine whether a gray value of the edge target pixel point is greater than the preset gray value threshold if the number of target pixel points corresponding to the gray value being less than the preset gray value threshold is not greater than the preset number;
the pixel determining unit is used for determining that the central target pixel point is a belt artifact pixel if the gray value of the edge target pixel point is larger than the preset gray value threshold value;
the number of the plurality of filtering units included in the preset filtering core and the length of the expansion unit are determined based on the length of the belt artifact to be detected, and the receptive field length of the preset filtering core is larger than the length of the belt artifact to be detected;
The number of the plurality of filtering units included in the preset filtering core is 5, and the preset number is 2;
the data acquisition module comprises:
the data acquisition sub-module is used for acquiring a bright field template, a dark field template and image data to be processed of an object to be detected of the security inspection equipment, wherein the bright field template is the X-ray signal intensity acquired by a detector under the condition that an X-ray source of the security inspection equipment is opened and a conveying belt is stationary, and the dark field template is the X-ray signal intensity acquired by the detector under the condition that the X-ray source of the security inspection equipment is closed and the conveying belt is stationary;
a gray value calculation sub-module for calculating gray values Cali of the pixel points according to the following formula based on the bright field template, the dark field template and the image data to be processed n :
R n =Air n -Bk n
Wherein, air n Bk for the bright field template data n Scan for the dark field template data n Bk for the image data to be processed n For the dark field template data, R n As bright field correction parameters, factor is correction scaling Factor;
the gray correction module is used for carrying out gray correction on all belt pseudo-image pixels after determining all the belt pseudo-image pixels included in the image data to be processed, and generating a security check image corresponding to the detected object after processing; or, the gray correction module is configured to: obtaining duplicate data which is completely the same as the image data to be processed; determining an artifact pixel point in the copy data corresponding to the belt artifact pixel in the image data to be processed based on the detected belt artifact pixel in the image data to be processed; and carrying out gray correction on the pseudo image pixels in the copied data to generate a security check image corresponding to the processed object to be checked.
10. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the method of any of claims 1-7 when executing a program stored on a memory.
11. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311139486.2A CN117314771A (en) | 2023-09-05 | 2023-09-05 | Belt artifact processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311139486.2A CN117314771A (en) | 2023-09-05 | 2023-09-05 | Belt artifact processing method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117314771A true CN117314771A (en) | 2023-12-29 |
Family
ID=89259384
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311139486.2A Pending CN117314771A (en) | 2023-09-05 | 2023-09-05 | Belt artifact processing method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117314771A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118154699A (en) * | 2024-04-30 | 2024-06-07 | 合肥埃科光电科技股份有限公司 | Calibration method, image afterglow correction method, device and storage medium |
-
2023
- 2023-09-05 CN CN202311139486.2A patent/CN117314771A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118154699A (en) * | 2024-04-30 | 2024-06-07 | 合肥埃科光电科技股份有限公司 | Calibration method, image afterglow correction method, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Han et al. | Infrared small target detection utilizing the multiscale relative local contrast measure | |
CN111667448B (en) | Image processing method, device and equipment | |
CN106920245B (en) | Boundary detection method and device | |
CN108898132B (en) | Terahertz image dangerous article identification method based on shape context description | |
CN109633633B (en) | Life signal enhancement method based on segmented classification enhancement processing | |
CN117314771A (en) | Belt artifact processing method and device, electronic equipment and storage medium | |
CN110084786B (en) | Automatic defect identification method for digital X-ray image with gradually-changed background | |
CN110889843B (en) | SAR image ship target detection method based on maximum stable extremal region | |
CN104486618A (en) | Video image noise detection method and device | |
CN101584587B (en) | Automatic calibration method for CT projection center | |
CN111612773B (en) | Thermal infrared imager and real-time automatic blind pixel detection processing method | |
CN110599479A (en) | Monitoring area change detection method and device and storage medium | |
Bellens et al. | Evaluating conventional and deep learning segmentation for fast X-ray CT porosity measurements of polymer laser sintered AM parts | |
CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
CN110490848B (en) | Infrared target detection method, device and computer storage medium | |
CN116188510B (en) | Enterprise emission data acquisition system based on multiple sensors | |
CN107369163A (en) | A kind of quick SAR image object detection method based on best entropy Double Thresholding Segmentation | |
CN113160092A (en) | Detector image correction method and system under object shielding condition | |
CN113052019A (en) | Target tracking method and device, intelligent equipment and computer storage medium | |
US10152774B2 (en) | Method and system for estimating point spread function | |
Xiao | Application of SSD core detection algorithm in intelligent visual monitoring of examination room | |
Mo et al. | Digital multimeter reading recognition for automation verification | |
Wang et al. | A novel algorithm for ship detection in SAR images | |
US8090189B1 (en) | Detection of thin line for selective sensitivity during reticle inspection | |
US10958899B2 (en) | Evaluation of dynamic ranges of imaging devices |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |