CN117670842B - Cloth cover horizontal bar detection method, device, equipment and storage medium - Google Patents
Cloth cover horizontal bar detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117670842B CN117670842B CN202311682676.9A CN202311682676A CN117670842B CN 117670842 B CN117670842 B CN 117670842B CN 202311682676 A CN202311682676 A CN 202311682676A CN 117670842 B CN117670842 B CN 117670842B
- Authority
- CN
- China
- Prior art keywords
- rectangle
- frequency domain
- width
- graph
- value
- 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.)
- Active
Links
- 239000004744 fabric Substances 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 238000010586 diagram Methods 0.000 claims abstract description 59
- 239000003365 glass fiber Substances 0.000 claims abstract description 39
- 238000001914 filtration Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000011218 segmentation Effects 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 26
- 238000004891 communication Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims 2
- 230000006870 function Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000009940 knitting Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000012779 reinforcing material Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of glass fiber detection, in particular to a cloth cover bar detection method, a device, equipment and a storage medium, which comprise the following steps: setting a monitoring area, a set width value and a set length value to obtain color image data; converting into gray image data; converting into a frequency domain diagram by utilizing a Fourier formula; filtering by using a notch filter; converting into a time domain diagram through inverse Fourier transform; performing enhancement processing and threshold segmentation to obtain segmented regions; performing a closing operation and an opening operation on the divided regions to obtain a connected region diagram; and performing rectangular fitting judgment, and alarming when the width is larger than a set width value and the length is larger than a set length value. The invention converts the collected color image data into a frequency domain image, filters the frequency domain image by utilizing a notch filter, screens out the positions of the transverse strips with the cloth cover, and then judges the sizes of the transverse strips by performing steps such as image enhancement, threshold segmentation and the like, thereby realizing the transverse strip detection of the glass fiber cloth cover.
Description
Technical Field
The invention relates to the technical field of glass fiber detection, in particular to a cloth cover horizontal bar detection method, a device, equipment and a storage medium.
Background
Glass fiber is an inorganic nonmetallic material with excellent performance, and has the advantages of good insulativity, good heat resistance and high mechanical strength, and is generally used as a reinforcing material of a composite material, an electric insulating material and a heat insulation material, and is mainly used as a material of a ship body, a storage tank, a cooling tower, a ship, a vehicle, a tank and a building structure.
When the high-speed glass fiber multi-axial warp knitting machine production line is used for producing, glass fibers are paved and then knitted, and the situation that the glass fibers are broken can occur, so that a gap is formed in the cloth cover after a certain layer is paved, and the gap is called a transverse bar. The common image preprocessing method is easy to be influenced by cloth surface lines to cause false alarm, and the detection of the glass fiber cloth surface by a new detection mode becomes a technical problem to be solved urgently.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
In view of at least one of the above technical problems, the present invention provides a method, an apparatus, a device and a storage medium for detecting a cloth cover bar, which detect the cloth cover bar by using a notch filter on a frequency domain diagram.
According to a first aspect of the present invention, there is provided a cloth cover rail detection method comprising the steps of:
s10: setting a monitoring area, a set width value and a set length value, and acquiring color image data of the glass fiber cloth cover;
S20: converting the color image data into grayscale image data;
s30: converting the gray image data into a frequency domain map by using a Fourier formula;
S40: filtering the frequency domain map by using a notch filter to generate a filtered frequency domain map;
S50: converting the filtered frequency domain map into a time domain map through inverse fourier transform;
S60: performing enhancement processing on the time domain graph, and performing threshold segmentation to obtain segmented regions;
S70: performing a closing operation and an opening operation on the divided regions to obtain a communication region diagram;
s80: and carrying out rectangular fitting on the communication area diagram, judging, and alarming when the width of the fitted rectangle is larger than the set width value and the length is larger than the set length value.
In some embodiments of the present invention, in step S40, the following steps are further included:
s41: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain graph, wherein the width of the first rectangle is the width of the frequency domain graph, the height of the first rectangle is single pixel height, the height of the second rectangle is the height of the frequency domain graph, and the width of the second rectangle is single pixel width;
s42: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
S43: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is high in the frequency domain graph, the third rectangle is wide in the frequency domain graph, the fourth rectangle is long in the frequency domain graph, and the width is set to be 50;
s44: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
S45: the output result is a filtered frequency domain plot.
In some embodiments of the present invention, in step S60, the following steps are further included:
S61: and carrying out contrast enhancement on the time domain graph, wherein the formula is as follows:
g′：＝g*Mult+Add
wherein, the gray value range is [ GMin, GMax ], Add＝-Mult*Gmin；
S62: and carrying out mean filtering on the time domain graph subjected to the contrast enhancement by using a mean filter of the size of the whole graph of the time domain graph, wherein the formula is as follows:
res：＝round((orig-mean)*Factor)+orig
The Factor value is set to be 1, the origin is the image gray value before the time domain image is filtered, the mean is the image gray value after the time domain image is filtered, and the round is the value of the (origin-mean) Factor calculation result to be rounded;
S63: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
s64: and outputting the pixel points as divided areas.
In some embodiments of the present invention, in step S80, the following steps are further included:
S81: separating non-connected areas of the connected area map;
s82: extracting the outline of the non-connected region;
S83: rectangular fitting is carried out on the outline by using the base weight;
s84: and judging the rectangle, and alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value.
According to a second aspect of the present invention, there is also provided a cloth cover rail detection device comprising:
and the acquisition module is used for: setting a monitoring area, a set width value and a set length value, and acquiring color image data of the glass fiber cloth cover;
an image processing module: converting the color image data into grayscale image data;
a frequency domain diagram conversion module: converting the gray image data into a frequency domain map by using a Fourier formula;
And the filtering processing module is used for: filtering the frequency domain map by using a notch filter to generate a filtered frequency domain map;
a time domain diagram conversion module: converting the filtered frequency domain map into a time domain map through inverse fourier transform;
An image enhancement module: performing enhancement processing on the time domain graph, and performing threshold segmentation to obtain segmented regions;
And the image communication module is used for: performing a closing operation and an opening operation on the divided regions to obtain a communication region diagram;
and a judging module: and carrying out rectangular fitting on the communication area diagram, judging, and alarming when the width of the fitted rectangle is larger than the set width value and the length is larger than the set length value.
In some embodiments of the present invention, in the filtering processing module, the filtering processing module further includes the following units:
A first rectangle and second rectangle generating unit: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain graph, wherein the width of the first rectangle is the width of the frequency domain graph, the height of the first rectangle is single pixel height, the height of the second rectangle is the height of the frequency domain graph, and the width of the second rectangle is single pixel width;
eliminating low frequency unit: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
Second rectangle and third rectangle generating unit: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is high in the frequency domain graph, the third rectangle is wide in the frequency domain graph, the fourth rectangle is long in the frequency domain graph, and the width is set to be 50;
high frequency unit is eliminated: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
a result output unit: the output result is a filtered frequency domain plot.
In some embodiments of the present invention, in the image enhancement module, the method further includes:
contrast enhancement unit: and carrying out contrast enhancement on the time domain graph, wherein the formula is as follows:
g′：＝g*Mult+Add
wherein, the gray value range is [ GMin, GMax ], Add＝--Mult*Gmin；
And the average filtering unit is used for: and carrying out mean filtering on the time domain graph subjected to the contrast enhancement by using a mean filter of the size of the whole graph of the time domain graph, wherein the formula is as follows:
res：＝round((orig-mean)*Factor)+orig
The Factor value is set to be 1, the origin is the image gray value before the time domain image is filtered, the mean is the image gray value after the time domain image is filtered, and the round is the value of the (origin-mean) Factor calculation result to be rounded;
threshold dividing unit: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
an image output unit: and outputting the pixel points as divided areas.
In some embodiments of the present invention, in step S80, the following steps are further included:
separating the non-connected region units: separating non-connected areas of the connected area map;
contour extraction unit: extracting the outline of the non-connected region;
rectangular fitting unit: rectangular fitting is carried out on the outline by using the base weight;
a result judgment unit: and judging the rectangle, and alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value.
According to a third aspect of the present invention there is also provided a cloth cover bar detection apparatus comprising a computer apparatus including a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method as described above when executing the computer program.
According to a fourth aspect of the present invention there is also provided a cloth cover bar detection storage medium comprising a storage medium having stored thereon a computer program which when executed by a processor performs the method described above.
The beneficial effects of the invention are as follows: the invention collects color image data on glass fiber, converts the color image data into gray image data, converts the gray image data into frequency domain image by Fourier formula, filters out background texture and integral brightness by notch filtering operation on the frequency domain image, converts into time domain image by inverse Fourier transform, extracts the area containing glass fiber cloth cover horizontal bar by image enhancement and threshold segmentation on the time domain image, connects the broken part of the glass fiber cloth cover horizontal bar by yarn by opening operation and closing operation, eliminates the position with protruding burr, makes the width of the glass fiber cloth cover horizontal bar more accurate, separates the non-connected area, extracts the outline of the area, fits rectangle, judges the fitted rectangle, and alarms when the length of rectangle is larger than the set length value and the width is larger than the set width value. According to the invention, the transverse bars on the glass fiber cloth cover are judged through visual recognition, the notch filter is used for screening the transverse bars on the glass fiber cloth cover, and then judgment is carried out, so that false alarm caused by the texture and the background brightness of the glass fiber cloth cover is reduced, and the production efficiency and the quality of the product are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a flow chart of steps of a method for detecting a cloth cover rail in an embodiment of the invention;
FIG. 2 is a schematic structural view of a cloth cover rail detection device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a computer device for detecting a cloth cover bar in an embodiment of the present invention;
FIG. 4 is a gray image data diagram of a cloth cover bar detection method according to an embodiment of the present invention;
FIG. 5 is a frequency domain diagram of a cloth cover bar detection method according to an embodiment of the present invention;
FIG. 6 is a diagram of a filtering frequency domain of a cloth cover cross bar detection method according to an embodiment of the present invention;
FIG. 7 is a time domain diagram of a method for detecting a cloth cover rail according to an embodiment of the present invention;
FIG. 8 is a segmented region of a cloth cover rail detection method in an embodiment of the present invention;
FIG. 9 is a diagram of a connected area of a method for detecting a cloth cover rail in an embodiment of the present invention;
Fig. 10 is a fitted rectangular chart of a cloth cover bar detection method in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
A cloth cover rail detection method as in figures 1 to 10,
S10: setting a monitoring area, a set width value and a set length value, acquiring color image data of the glass fiber cloth cover, erecting a camera above the glass fiber cloth cover, collecting the color image data of the glass fiber cloth cover, and setting various parameters.
S20: the color image data is converted into gray image data, and the color image data is converted into gray image data, as shown in fig. 4, the gray values formed by the refraction of the glass fibers, the binding yarns and the cloth cover transverse strips on the glass fiber cloth are different, and the difference of the gray values among the areas is used for screening and judging.
S30: converting gray image data into a frequency domain diagram by using a Fourier formula, wherein the M.times.N image two-dimensional discrete Fourier formula is as follows:
As shown in fig. 5, the image signal can be converted into a frequency domain map by fourier transform, the center position of the frequency domain map being a direct current component, the farther from the center, the higher the frequency. It should be noted that the fourier transform is a basic operation in digital signal processing, and is not described herein.
S40: the frequency domain map is filtered by a notch filter to generate a filtered frequency domain map, and as shown in fig. 6, the filtered frequency domain map is filtered to filter out the background texture and the overall brightness in the frequency domain map.
S50: the filtered frequency domain diagram is converted into a time domain diagram through inverse fourier transform, as shown in fig. 7, the filtered frequency domain diagram generated through the steps is converted into the time domain diagram through inverse fourier transform, and only a part with a glass fiber cloth cover cross bar remains in the time domain diagram, wherein the inverse fourier transform formula is as follows:
it should be noted here that the inverse fourier transform is a basic operation in digital signal processing, and is not described here in detail as in the prior art.
S60: the time domain image is enhanced, and threshold segmentation is performed to obtain segmented regions, in order to make the parts of the glass fiber cloth cover horizontal bars clearer, the time domain image is subjected to image enhancement, as shown in fig. 8, the gray values of the pixel points can be changed under the condition that the coordinate information of the pixel points is not changed by performing the image enhancement on the time domain image, so that the contrast of the image is pulled, and the black places and the white places in the gray image data are darker.
S70: the split areas are subjected to a closing operation and an opening operation to obtain a connected area diagram, and as shown in fig. 9, the split areas subjected to image enhancement may be required to be subjected to the closing operation and the opening operation first because the binding yarns on the glass fiber cloth cover separate the horizontal bar areas. Firstly, the extracted divided areas are subjected to closed operation, the disconnected areas are connected, and then the divided areas are subjected to open operation, so that protruding burrs are eliminated, the periphery of the divided areas is smoother, and meanwhile, the subsequent width judgment is more accurate. It should be noted here that the core diameter of the open operation is smaller than that of the closed operation, and the size of the core can be set according to the size requirement for the glass fiber cloth cover rail. In some embodiments of the present invention, the closed op-erating kernel diameter is set to 3.5 and the open op-erating kernel diameter is set to 2.5, preventing the connected open areas from being opened again.
S80: and carrying out rectangular fitting on the communication area diagram, judging, and alarming when the width of the fitted rectangle is larger than a set width value and the length is larger than a set length value. As shown in fig. 10, the fitted rectangle is subjected to size judgment to judge whether the size of the glass fiber cloth cover horizontal bar meets the alarm requirement. When the length and the width are both greater than the set values, alarming is carried out; and if the length is larger than the set length value and the width is smaller than the set width value, detecting the next gray image data, and if the length is smaller than the set length value and the width is larger than the set width value, detecting the next gray image data, and sequentially and circularly detecting the gray image data. It should be noted that, at present, the set width value of the glass fiber cloth cover horizontal bar is 4mm, the set length value is 27mm (i.e. 16 pixels wide and 108 pixels long), and different set width values and set length values can be set according to different requirements.
The invention is characterized in that color image data is collected on glass fiber, the color image data is converted into gray image data, the gray image data is converted into frequency domain image by utilizing Fourier formula, background texture and whole brightness are filtered through notch filtering operation on the frequency domain image, then the frequency domain image is converted into time domain image by inverse Fourier transform, the area containing the glass fiber cloth surface cross bar is extracted through image enhancement and threshold segmentation on the time domain image, then the broken part of the glass fiber cloth surface cross bar by yarns is connected through opening operation and closing operation, the position with protruding burrs is eliminated, the width of the glass fiber cloth surface cross bar is more accurate, finally the non-connected area is separated, the outline of the area is extracted, rectangular fitting is carried out, the rectangle after fitting is judged, and when the length of the rectangle is larger than the set length value and the width is larger than the set width value, the alarm is carried out. According to the invention, the transverse bars on the glass fiber cloth cover are judged through visual recognition, the notch filter is used for screening the transverse bars on the glass fiber cloth cover, and then judgment is carried out, so that false alarm caused by the texture and the background brightness of the glass fiber cloth cover is reduced, and the production efficiency and the quality of the product are improved.
In some embodiments of the present invention, in step S40, the following steps are further included:
s41: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain diagram, wherein the width of the first rectangle is the width of the frequency domain diagram, the height of the first rectangle is the height of a single pixel, the height of the second rectangle is the height of the frequency domain diagram, and the width of the second rectangle is the width of the single pixel;
S42: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
S43: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is the frequency domain graph, the fourth rectangle is the frequency domain graph, and the fourth rectangle is the set width 50;
s44: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
S45: the output result is a filtered frequency domain plot.
And generating a first rectangle and a second rectangle with single pixel width on the central pixel point of the frequency domain diagram, and filling the interiors of the first rectangle and the second rectangle to be 0, so that signals of a low-frequency part are eliminated, and a texture part in the image is eliminated. And generating a third rectangle and a fourth rectangle, and filling the non-overlapped part of the third rectangle and the fourth rectangle into 0, so that signals of high-frequency parts are eliminated. Filtering the frequency domain image, and filtering out background textures and overall brightness. In some embodiments of the present invention, the width of the fourth rectangle may be set to 50, or may be adjusted according to the actual situation.
In some embodiments of the present invention, in step S60, the following steps are further included:
S61: contrast enhancement is carried out on the time domain diagram, and the formula is as follows:
g′：＝g*Mult+Add
wherein, the gray value range is [ GMin, GMax ], Add＝-Mult*Gmin；
S62: and (3) carrying out mean value filtering on the time domain diagram subjected to contrast enhancement by using a mean value filter with the size of the whole diagram of the time domain diagram, wherein the formula is as follows:
res：＝round((orig-mean)*Factor)+orig
The Factor value is set to be 1, orig is the image gray value before time domain image filtering, mean is the image gray value after time domain image filtering, and round is the value of the Factor calculation result;
S63: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
s64: the pixel points are output as divided regions.
When the enhancement processing is carried out on the time domain image, the contrast enhancement is carried out firstly, the gray value is amplified to 0-255, and the contrast of gray image data is enlarged through the arrangement of the maximum value and the minimum value of pixels, so that the black place in the gray image data is darker, and the bright place is brighter. And then the contrast enhancement is carried out through the mean value filter, and the gray value scaling is carried out on the time domain graph, so that the contrast of the time domain graph is stronger and can be seen to be clearer.
In some embodiments of the present invention, in step S80, the following steps are further included:
s81: separating the non-connected region of the connected region map,
S82: the outline of the non-connected region is extracted,
S83: rectangular fitting is performed on the contour by using the graph basis weight,
S84: judging the rectangle, alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value,
According to the technical scheme, the extracted connected region graph is firstly separated into non-connected regions, the non-connected regions in the connected region graph are separated, the connected region graph is separated into a plurality of regions, the regions are judged, firstly, the extracted contours of the separated regions are required to be extracted, then the rectangular fitting is carried out on the extracted contours by using the basis weight of the graph, finally, the fitted house type is judged, and when the fitted rectangular width is larger than the set width value and the length is larger than the set length value, the fact that the area of the glass fiber cloth cover transverse bar is larger than the set value is indicated, and an alarm is given.
It should be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, an apparatus, an electronic device, or a computer storage medium product, and thus, embodiments of the present application may be implemented entirely in hardware embodiments, embodiments in which hardware is combined with software, or embodiments in which software is used, an experimental detection process data processing apparatus in the embodiments of the present application will be described below, and the embodiments of the apparatus hereinafter correspond to the embodiments of the method above, and those skilled in the art will understand, based on the foregoing description, the following implementation will not be described in detail herein.
The cloth cover rail detection device as shown in fig. 2 includes:
and the acquisition module is used for: setting a monitoring area, a set width value and a set length value, and acquiring color image data of the glass fiber cloth cover;
an image processing module: converting the color image data into gray scale image data;
A frequency domain diagram conversion module: converting the gray image data into a frequency domain map by using a Fourier formula;
and the filtering processing module is used for: filtering the frequency domain map by using a notch filter to generate a filtered frequency domain map;
a time domain diagram conversion module: converting the filtered frequency domain map into a time domain map through inverse Fourier transform;
An image enhancement module: performing enhancement processing on the time domain graph, and performing threshold segmentation to obtain segmented regions;
And the image communication module is used for: performing a closing operation and an opening operation on the divided regions to obtain a connected region diagram;
and a judging module: and carrying out rectangular fitting on the communication area diagram, judging, and alarming when the width of the fitted rectangle is larger than a set width value and the length is larger than a set length value.
In some embodiments of the present invention, in the filtering processing module, the filtering processing module further includes:
A first rectangle and second rectangle generating unit: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain diagram, wherein the width of the first rectangle is the width of the frequency domain diagram, the height of the first rectangle is the height of a single pixel, the height of the second rectangle is the height of the frequency domain diagram, and the width of the second rectangle is the width of the single pixel;
eliminating low frequency unit: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
Second rectangle and third rectangle generating unit: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is the frequency domain graph, the fourth rectangle is the frequency domain graph, and the fourth rectangle is the set width 50;
high frequency unit is eliminated: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
a result output unit: the output result is a filtered frequency domain plot.
In some embodiments of the present invention, in the image enhancement module, the method further includes:
Contrast enhancement unit: contrast enhancement is carried out on the time domain diagram, and the formula is as follows:
g′：＝g*Mult+Add
wherein, the gray value range is [ GMin, GMax ], Add＝-Mult*Gnmin；
And the average filtering unit is used for: and (3) carrying out mean value filtering on the time domain diagram subjected to contrast enhancement by using a mean value filter with the size of the whole diagram of the time domain diagram, wherein the formula is as follows:
res：＝round((orig-mean)*Factor)+orig
The Factor value is set to be 1, orig is the image gray value before time domain image filtering, mean is the image gray value after time domain image filtering, and round is the value of the Factor calculation result;
threshold dividing unit: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
An image output unit: the pixel points are output as divided regions.
In some embodiments of the present invention, in step S80, the following steps are further included:
separating the non-connected region units: separating non-connected areas of the connected area diagram;
contour extraction unit: extracting the outline of the non-connected region;
rectangular fitting unit: rectangular fitting is carried out on the outline by using the graph base weight;
A result judgment unit: and judging the rectangle, and alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value.
In the following sections of the embodiments of the present invention, the embodiments of the electronic device and the computer storage medium in the embodiments of the present invention are described, and the embodiments of the electronic device and the computer storage medium in the following correspond to the embodiments of the method in the foregoing, and those skilled in the art may understand the following implementation process based on the foregoing description, which is not described in detail herein.
As shown in fig. 3, a schematic structural diagram of a computer device according to an embodiment of the present application is provided, and a computer device 400 according to an embodiment of the present application includes: the memory 420, the processor 410, and a computer program stored on the memory 420 and executable on the processor 410, the processor 410 implementing the method described above when executing the computer program.
The embodiment of the present application further provides a storage medium 430 on which a computer program is stored, which when executed by the processor 410 implements the above-described method.
The storage medium 430 may be implemented by any type of volatile or nonvolatile Memory device or combination thereof, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The meaning of "a plurality of" is two or more, unless specifically defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily for the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (8)
1. The cloth cover horizontal bar detection method is characterized by comprising the following steps:
s10: setting a monitoring area, a set width value and a set length value, and acquiring color image data of the glass fiber cloth cover;
S20: converting the color image data into grayscale image data;
s30: converting the gray image data into a frequency domain map by using a Fourier formula;
S40: filtering the frequency domain map by using a notch filter to generate a filtered frequency domain map;
S50: converting the filtered frequency domain map into a time domain map through inverse fourier transform;
S60: performing enhancement processing on the time domain graph, and performing threshold segmentation to obtain segmented regions;
S70: performing a closing operation and an opening operation on the divided regions to obtain a communication region diagram;
s80: performing rectangular fitting and judging on the communication area graph, and alarming when the width of the fitted rectangle is larger than the set width value and the length is larger than the set length value;
In step S40, the method further includes the steps of:
s41: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain graph, wherein the width of the first rectangle is the width of the frequency domain graph, the height of the first rectangle is single pixel height, the height of the second rectangle is the height of the frequency domain graph, and the width of the second rectangle is single pixel width;
s42: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
S43: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is high in the frequency domain graph, the third rectangle is wide in the frequency domain graph, the fourth rectangle is long in the frequency domain graph, and the width is set to be 50;
s44: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
S45: the output result is a filtered frequency domain plot.
2. The cloth cover rail detection method according to claim 1, further comprising the step of, in step S60:
S61: and carrying out contrast enhancement on the time domain graph, wherein the formula is as follows:
wherein, the gray value range is [ GMin, GMax ], ，/>；
S62: and carrying out mean filtering on the time domain graph subjected to the contrast enhancement by using a mean filter of the whole graph size of the time domain graph, and enhancing the contrast by using the mean filter, wherein the formula is as follows:
Wherein the Factor value is set to 1, orig is the image gray value before the time domain diagram is filtered, mean is the image gray value after the time domain diagram is filtered, and round is Rounding the value of the calculation result;
s63: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
s64: and outputting the pixel points as divided areas.
3. The cloth cover rail detection method according to claim 1, further comprising the step of, in step S80:
S81: separating non-connected areas of the connected area map;
s82: extracting the outline of the non-connected region;
S83: rectangular fitting is carried out on the outline by using the base weight;
s84: and judging the rectangle, and alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value.
4. A cloth cover rail detection device, comprising:
and the acquisition module is used for: setting a monitoring area, a set width value and a set length value, and acquiring color image data of the glass fiber cloth cover;
an image processing module: converting the color image data into grayscale image data;
a frequency domain diagram conversion module: converting the gray image data into a frequency domain map by using a Fourier formula;
And the filtering processing module is used for: filtering the frequency domain map by using a notch filter to generate a filtered frequency domain map;
a time domain diagram conversion module: converting the filtered frequency domain map into a time domain map through inverse fourier transform;
An image enhancement module: performing enhancement processing on the time domain graph, and performing threshold segmentation to obtain segmented regions;
And the image communication module is used for: performing a closing operation and an opening operation on the divided regions to obtain a communication region diagram;
And a judging module: performing rectangular fitting and judging on the communication area graph, and alarming when the width of the fitted rectangle is larger than the set width value and the length is larger than the set length value;
the filtering processing module further comprises the following units:
A first rectangle and second rectangle generating unit: generating a first rectangle and a second rectangle on a central point pixel of the frequency domain graph, wherein the width of the first rectangle is the width of the frequency domain graph, the height of the first rectangle is single pixel height, the height of the second rectangle is the height of the frequency domain graph, and the width of the second rectangle is single pixel width;
eliminating low frequency unit: filling the first rectangle and the second rectangle into 0, and generating a preprocessing frequency domain diagram;
Second rectangle and third rectangle generating unit: generating a third rectangle and a fourth rectangle on the preprocessing frequency domain graph, wherein the third rectangle is high in the frequency domain graph, the third rectangle is wide in the frequency domain graph, the fourth rectangle is long in the frequency domain graph, and the width is set to be 50;
high frequency unit is eliminated: filling the non-overlapping area of the third rectangle and the fourth rectangle to be 0;
a result output unit: the output result is a filtered frequency domain plot.
5. The cloth cover rail detection device of claim 4, further comprising, in the image enhancement module:
contrast enhancement unit: and carrying out contrast enhancement on the time domain graph, wherein the formula is as follows:
wherein, the gray value range is [ GMin, GMax ], ，/>；
And the average filtering unit is used for: and carrying out mean filtering on the time domain graph subjected to the contrast enhancement by using a mean filter of the whole graph size of the time domain graph, and enhancing the contrast by using the mean filter, wherein the formula is as follows:
Wherein the Factor value is set to 1, orig is the image gray value before the time domain diagram is filtered, mean is the image gray value after the time domain diagram is filtered, and round is Rounding the value of the calculation result;
threshold dividing unit: performing threshold segmentation to extract pixel points with gray values between 210 and 255;
an image output unit: and outputting the pixel points as divided areas.
6. The cloth cover rail detection device of claim 4, further comprising, in step S80, the steps of:
separating the non-connected region units: separating non-connected areas of the connected area map;
contour extraction unit: extracting the outline of the non-connected region;
rectangular fitting unit: rectangular fitting is carried out on the outline by using the base weight;
a result judgment unit: and judging the rectangle, and alarming when the fitted rectangle is larger than the set width value and the length is larger than the set length value.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-3 when executing the computer program.
8. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311682676.9A CN117670842B (en) | 2023-12-07 | 2023-12-07 | Cloth cover horizontal bar detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311682676.9A CN117670842B (en) | 2023-12-07 | 2023-12-07 | Cloth cover horizontal bar detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117670842A CN117670842A (en) | 2024-03-08 |
| CN117670842B true CN117670842B (en) | 2024-06-04 |
Family
ID=90084316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311682676.9A Active CN117670842B (en) | 2023-12-07 | 2023-12-07 | Cloth cover horizontal bar detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117670842B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056542A (en) * | 2016-05-19 | 2016-10-26 | 西安交通大学 | Interferogram background removing method based on frequency domain filtering |
| CN109934802A (en) * | 2019-02-02 | 2019-06-25 | 浙江工业大学 | A kind of Fabric Defects Inspection detection method based on Fourier transformation and morphological image |
| CN110111301A (en) * | 2019-03-21 | 2019-08-09 | 广东工业大学 | Metal based on frequency-domain transform aoxidizes surface defect visible detection method |
| CN110838093A (en) * | 2019-11-05 | 2020-02-25 | 安徽大学 | Efficient and high-quality fMOST or MOST microscopic image stripe noise removing method |
| CN111383186A (en) * | 2018-12-29 | 2020-07-07 | Tcl集团股份有限公司 | Image processing method and device and terminal equipment |
| CN111915515A (en) * | 2020-07-21 | 2020-11-10 | 无锡声亚医疗科技有限公司 | Method for removing noise in ultrasonic image, ultrasonic equipment and storage medium |
| CN113706521A (en) * | 2021-09-08 | 2021-11-26 | 常州市新创智能科技有限公司 | Carbon fiber surface hairiness detection method and device, storage medium and electronic equipment |
| CN114091620A (en) * | 2021-12-01 | 2022-02-25 | 常州市宏发纵横新材料科技股份有限公司 | Template matching detection method, computer equipment and storage medium |
| CN114998325A (en) * | 2022-07-19 | 2022-09-02 | 新力环境科技(山东)有限公司 | Air conditioner radiating tube welding defect detection method |
| CN116563223A (en) * | 2023-04-11 | 2023-08-08 | 新创碳谷集团有限公司 | Glass fiber yarn winding roller detection method, equipment and storage medium |
| CN116823796A (en) * | 2023-07-13 | 2023-09-29 | 常州市新创智能科技有限公司 | Method, device, equipment and medium for detecting transverse strips of non-uniform glass fiber cloth |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101767564B1 (en) * | 2015-11-12 | 2017-08-11 | 성균관대학교산학협력단 | A method of analysing images of rod-like particles |
-
2023
- 2023-12-07 CN CN202311682676.9A patent/CN117670842B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056542A (en) * | 2016-05-19 | 2016-10-26 | 西安交通大学 | Interferogram background removing method based on frequency domain filtering |
| CN111383186A (en) * | 2018-12-29 | 2020-07-07 | Tcl集团股份有限公司 | Image processing method and device and terminal equipment |
| CN109934802A (en) * | 2019-02-02 | 2019-06-25 | 浙江工业大学 | A kind of Fabric Defects Inspection detection method based on Fourier transformation and morphological image |
| CN110111301A (en) * | 2019-03-21 | 2019-08-09 | 广东工业大学 | Metal based on frequency-domain transform aoxidizes surface defect visible detection method |
| CN110838093A (en) * | 2019-11-05 | 2020-02-25 | 安徽大学 | Efficient and high-quality fMOST or MOST microscopic image stripe noise removing method |
| CN111915515A (en) * | 2020-07-21 | 2020-11-10 | 无锡声亚医疗科技有限公司 | Method for removing noise in ultrasonic image, ultrasonic equipment and storage medium |
| CN113706521A (en) * | 2021-09-08 | 2021-11-26 | 常州市新创智能科技有限公司 | Carbon fiber surface hairiness detection method and device, storage medium and electronic equipment |
| CN114091620A (en) * | 2021-12-01 | 2022-02-25 | 常州市宏发纵横新材料科技股份有限公司 | Template matching detection method, computer equipment and storage medium |
| CN114998325A (en) * | 2022-07-19 | 2022-09-02 | 新力环境科技(山东)有限公司 | Air conditioner radiating tube welding defect detection method |
| CN116563223A (en) * | 2023-04-11 | 2023-08-08 | 新创碳谷集团有限公司 | Glass fiber yarn winding roller detection method, equipment and storage medium |
| CN116823796A (en) * | 2023-07-13 | 2023-09-29 | 常州市新创智能科技有限公司 | Method, device, equipment and medium for detecting transverse strips of non-uniform glass fiber cloth |
Non-Patent Citations (2)
| Title |
|---|
| 图像条带噪声的去除方法;陶胜;;洛阳理工学院学报(自然科学版);20170925(第03期);全文 * |
| 红外成像中图像质量提升算法研究;曾庆杰;《中国博士学位论文全文数据库信息科技辑》;20220415(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117670842A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805829B (en) | Image data processing method, device, equipment and computer readable storage medium | |
| US20080273807A1 (en) | Compression of digital images of scanned documents | |
| CN113610774B (en) | Glass scratch defect detection method, system, device and storage medium | |
| CN114926436A (en) | Defect detection method for periodic pattern fabric | |
| CN113870233B (en) | Binding yarn detection method, computer equipment and storage medium | |
| DE60302946T2 (en) | Image segmentation method and apparatus for MRC-based presentation of documents | |
| CN117670842B (en) | Cloth cover horizontal bar detection method, device, equipment and storage medium | |
| Liu et al. | Infrared and visible image fusion based on region of interest detection and nonsubsampled contourlet transform | |
| CN116596802B (en) | Binding yarn extraction method, device, equipment and medium under complex background | |
| CN115908404B (en) | Image stripe interference detection method and device, electronic equipment and medium | |
| CN102509265B (en) | Digital image denoising method based on gray value difference and local energy | |
| CN112834875A (en) | Partial discharge pulse segmentation method and system | |
| CN113379671A (en) | Partial discharge diagnosis system and diagnosis method for switch equipment | |
| CN116823796A (en) | Method, device, equipment and medium for detecting transverse strips of non-uniform glass fiber cloth | |
| CN116152225A (en) | Inductance touch screen production process adjusting method and system | |
| CN117670843B (en) | Method, device, equipment and storage medium for detecting broken yarn of color yarn | |
| CN115861220A (en) | Cold-rolled strip steel surface defect detection method and system based on improved SSD algorithm | |
| CN117745702A (en) | Carbon fiber cloth cover horizontal bar detection method, device, equipment and storage medium | |
| CN113516608B (en) | Method and device for detecting defects of tire and tire detecting equipment | |
| CN112465835A (en) | Method for jadeite image segmentation and model training method | |
| CN118297904A (en) | Carbon fiber cloth cover light-color foreign matter detection system and method | |
| DE102019128219A1 (en) | An image processing method | |
| Clausi et al. | Feature fusion for image texture segmentation | |
| CN117830141B (en) | Method, medium, equipment and device for removing vertical stripe noise of infrared image | |
| CN117670840A (en) | Method, device, equipment and storage medium for detecting black foreign matter on edge |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |