CN111369531B - Image definition scoring method, device and storage device - Google Patents
Image definition scoring method, device and storage device Download PDFInfo
- Publication number
- CN111369531B CN111369531B CN202010144990.1A CN202010144990A CN111369531B CN 111369531 B CN111369531 B CN 111369531B CN 202010144990 A CN202010144990 A CN 202010144990A CN 111369531 B CN111369531 B CN 111369531B
- Authority
- CN
- China
- Prior art keywords
- image
- scored
- value
- corner
- brightness quality
- 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
- 238000013077 scoring method Methods 0.000 title abstract description 14
- 238000000034 method Methods 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- 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
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses a scoring method, equipment and a storage device for image definition. The scoring method of the image definition comprises the following steps: acquiring an image to be scored; analyzing at least one feature of the image to be scored to obtain a score corresponding to each feature, wherein the at least one feature comprises at least one of image brightness quality, image corner number and image corner spatial distribution; and obtaining the definition score of the image to be scored by using the score of at least one feature. By the aid of the scheme, accuracy of image scoring can be improved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, an apparatus, and a storage device for scoring image sharpness.
Background
Image technology has been widely used, for example, evidence taking for traffic violation penalties and the like. Taking the example of shooting license plate images of vehicles coming and going during the evidence taking of traffic violation penalty, because the actual condition of vehicle traffic is complex, not all images are clear and need subsequent storage and utilization, therefore, the unclear images need to be filtered. Thus, in the face of a large number of images, it is necessary to score the sharpness of the images and then filter out the unclear images. At present, a great deal of manpower is required for subjective evaluation of image definition according to subjective opinion grading, time is consumed, and cost is high; the objective evaluation of the image definition includes a full-reference image method, a half-reference image method and a no-reference image method, wherein if the full-reference image method and the half-reference image method are adopted, it is often difficult to obtain a clear image as a reference, and the direct scoring of the no-reference image method is not accurate enough.
Based on the above, how to improve the accuracy of image scoring is a urgent problem to be solved for the problem of inaccurate image definition scoring.
Disclosure of Invention
The application mainly solves the technical problem of providing a scoring method, equipment and a storage device for image definition, which can score the image definition and improve the accuracy of image scoring.
In order to solve the above problems, a first aspect of the present application provides a scoring method for image sharpness, including: acquiring an image to be scored; analyzing at least one feature of the image to be scored to obtain a score corresponding to each feature, wherein the at least one feature comprises at least one of image brightness quality, image corner number and image corner spatial distribution; and obtaining the definition score of the image to be scored by using the score of at least one feature.
To solve the above-mentioned problems, a second aspect of the present application provides an electronic device, including a processor and a memory coupled to each other, wherein the processor is configured to execute a computer program stored in the memory to perform the method for scoring the sharpness of an image according to the first aspect.
In order to solve the above-mentioned problems, a third aspect of the present application provides a storage device storing a scoring method capable of realizing the image sharpness of the above-mentioned first aspect.
In the scheme, an image to be scored is obtained; analyzing at least one feature of the image to be scored to obtain a score corresponding to each feature, wherein the at least one feature comprises at least one of image brightness quality, image corner number and image corner spatial distribution; and obtaining the definition score of the image to be scored by using the score of at least one feature. By the mode, the image definition can be scored, and the accuracy of image scoring is improved.
Drawings
FIG. 1 is a flowchart of an embodiment of a method for scoring image sharpness according to the present application;
FIG. 2 is a flow chart of another embodiment of the image sharpness scoring method of the present application;
FIG. 3 is a flowchart illustrating a scoring method for image sharpness according to another embodiment of the present application, step S203;
FIG. 4 is a flowchart illustrating another embodiment of the method for scoring image sharpness in accordance with the present application, step S203;
FIG. 5 is a schematic diagram of a frame of an embodiment of an electronic device of the present application;
FIG. 6 is a schematic diagram of an embodiment of an electronic device of the present application;
FIG. 7 is a schematic diagram of a frame of an embodiment of a storage device of the present application;
Detailed Description
The following describes embodiments of the present application in detail with reference to the drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a method for scoring image sharpness according to the present application. Specifically, the method of the embodiment comprises the following steps:
step S101: and obtaining an image to be scored.
The image to be scored is an image such as a license plate image. The image to be scored can be directly shot by the image shooting equipment, or can be obtained by extracting the whole image containing the image to be scored after the image shooting equipment shoots the whole image containing the image to be scored. Taking the image to be scored as the license plate image as an example, the license plate image can be obtained by directly shooting the license plate image through the image shooting equipment, or the license plate image can be obtained by extracting the area where the license plate image in the whole image is located after the whole image containing the license plate image is shot by the image shooting equipment.
The image to be scored may be an unprocessed original image, a converted gray image, or a denoised noise reduction image, which is not particularly limited herein. It will be appreciated that the original image described above is an image that can be algorithmically changed to a gray scale image. In an embodiment, the image to be scored is an unprocessed original image, and the step S102 and subsequent steps are performed after the image to be scored is subjected to the graying processing by the algorithm.
Step S102: and analyzing at least one feature of the image to be scored to obtain the score corresponding to each feature.
At least one feature of the application comprises at least one of image brightness quality, image corner number and image corner spatial distribution, and can also comprise other features for evaluating image definition.
When analyzing the image brightness quality of the image to be scored, acquiring a first average pixel value of the image to be scored; obtaining the image brightness quality of the image to be scored by using the first average pixel value; based on the image brightness quality, a score corresponding to the image brightness quality is obtained. The first average pixel value is an average value of pixel values of pixel points in the image to be scored. The image brightness quality is the evaluation of brightness or darkness of the image to be scored, and can reflect the image definition.
Specifically, all pixel values of each pixel point of the image to be scored are obtained, pixel value accumulation is carried out, and the accumulated pixel values are divided by the number of pixels, namely, a first average pixel value of the image to be scored is obtained. In another embodiment, the first average pixel value may also be an average value of pixel values of partial pixels of the image to be scored. The first average pixel value is used for converting into image brightness quality for linearly evaluating the image brightness quality, wherein the larger the image brightness quality is, the clearer the image is. And obtaining the corresponding score of the image brightness quality after obtaining the image brightness quality. The manner of obtaining the corresponding score by the image brightness quality is not limited, and the corresponding relation between the image brightness quality and the score corresponding to the image brightness quality can be preset, and the score can be correspondingly obtained after the image brightness quality is obtained, for example, when the image brightness quality is 0.5-1, the corresponding score is 80-100; the corresponding score of the image brightness quality can be calculated by using a preset formula; the average value of the image brightness quality can be obtained by adopting any mode to obtain the corresponding score after the image brightness quality is obtained for a plurality of times.
When the number of image corner points of the image to be scored is analyzed, the number of corner points belonging to a preset type in the image to be scored is obtained; and obtaining the score corresponding to the number of the image corner points based on the number of the corner points. The preset types of corner points include, but are not limited to Harris corner points. When the angular points of the image to be scored are acquired, all the angular points in the image to be scored can be acquired, and part of the angular points in the image to be scored can also be acquired.
In an embodiment, based on the number of corner points, the specific process of obtaining the score corresponding to the number of corner points of the image is as follows: and obtaining the arctangent function value of the product of the corner number and the fourth constant, obtaining the product of the fifth constant and the arctangent function value, and taking the minimum value in the product of the fifth constant and the arctangent function value and the second preset value as the corresponding fraction of the image corner number. The values of the fourth constant and the fifth constant can be customized by a user.
By scoring the number of image corner points, the influence of the edge characteristics of the frame of the image to be scored on the definition of the image to be scored can be avoided. When the image to be scored contains characters, the corners are generally distributed in the character parts, so that the characters in the image to be scored can be scored and the prior of the characters is considered when the number of the corners of the image is scored, and the influence of the edge characteristics of the frame of the image to be scored on the definition of the image to be scored is avoided.
When the spatial distribution of image corner points of the image to be scored is analyzed, the position information of corner points belonging to a preset type in the image to be scored is obtained; and obtaining the score corresponding to the spatial distribution of the image corner based on the position information of the corner. The preset types of corner points include, but are not limited to Harris corner points. When the spatial distribution of the image corner points of the image to be scored is obtained, the preset types of the corner points are the same as the preset types when the number of the image corner points of the image to be scored is obtained, and the preset types are Harris corner points.
In an embodiment, the position information is a first axis coordinate and a second axis coordinate, and when the score corresponding to the spatial distribution of the image corner is obtained based on the position information of the corner, the first axis coordinate and the second axis coordinate of each corner are normalized. Acquiring a first standard deviation of a normalized first axis coordinate of the corner point, and acquiring a second standard deviation of a normalized second axis coordinate of the corner point; and obtaining a mean value between the square of the first standard deviation and the square of the second standard deviation, and taking the product of the square root of the mean value and a third preset value as a score corresponding to the spatial distribution of the image corner points.
And scoring the spatial distribution of the image corner points to enable the scoring result to be more accordant with the specific object characteristics of the image to be scored. When the image to be scored contains characters, the characters are uniformly distributed in the image to be scored, and the spatial distribution of the image corner points is scored, so that the error of the image definition scoring result to be scored caused by the aggregation of the image corner points can be reduced.
One or more characteristics of the image brightness quality, the image corner number and the image corner spatial distribution can be selected at will for analysis, so that corresponding scores are obtained and serve as the basis for scoring the definition of the image to be scored.
Step S103: and obtaining the definition score of the image to be scored by using the score of at least one feature.
And after the score of each feature is obtained, weighting and summing the scores of at least one feature to obtain the definition score of the image to be scored. When at least one feature of image brightness quality, image corner number and image corner space distribution is selected to score the definition of the image to be scored, the sum of the weights of all the selected features is 1, and the weight of each feature can be customized. For example, when the sharpness score of the image to be scored is obtained by using the scores of three features, namely, the image brightness quality, the number of image corners and the spatial distribution of the image corners, the weight of the image brightness quality is 0.2, the weight of the number of the image corners is 0.5, and the weight of the spatial distribution of the image corners is 0.3.
Acquiring an image to be scored; analyzing at least one feature of the image to be scored to obtain a score corresponding to each feature, wherein the at least one feature comprises at least one of image brightness quality, image corner number and image corner spatial distribution; and obtaining the definition score of the image to be scored by using the score of at least one feature. By the mode, the image definition can be scored, and the accuracy of image scoring is improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating another embodiment of a method for scoring image sharpness according to the present application. Specifically, the method of the embodiment comprises the following steps:
step S201: and obtaining an image to be scored.
In this embodiment, the image to be scored is an original image without any processing, which is a color chart obtained by photographing by the image photographing apparatus.
Step S202: and carrying out graying treatment on the image to be scored.
And carrying out graying treatment on the colored image to be scored so as to convert the colored image to a gray scale image. The graying process is a prior art process, for example, converting a BMP (Bitmap) of three channels into a single-channel gray scale map.
In an embodiment, the image to be scored after the graying process may be subjected to a smoothing denoising process. In the denoising process, any filter and any denoising algorithm in the prior art may be selected, for example, a bilateral filter is selected, the denoising algorithm with edge protection capability is used to denoise the image to be scored after the graying process, and the image to be scored after the denoising is obtained, so as to perform the step of the scoring method of the definition of the subsequent image.
Step S203: and analyzing at least one feature of the image to be scored after the graying treatment to obtain the score corresponding to each feature.
In this embodiment, the image brightness quality of the image to be scored after the graying treatment is analyzed, and a specific description of obtaining the score corresponding to the image brightness quality can be referred to fig. 3. Fig. 3 is a flow chart of step S203 of another embodiment of the image sharpness scoring method according to the present application, specifically, step S203 includes the following steps:
step S2031: a first average pixel value of the image to be scored is obtained.
And obtaining all pixel values of each pixel point of the image to be scored, accumulating the pixel values, dividing the accumulated pixel values by the number of pixels, and obtaining a first average pixel value of the image to be scored.
Step S2032: and obtaining the image brightness quality of the image to be scored by using the first average pixel value.
The first average pixel value is normalized to the second average pixel value. And obtaining the image brightness quality of the image to be scored based on the second average pixel value. Specifically, after the first average pixel value is acquired, the first average pixel value is divided by 255 so that the first average pixel value is normalized to a range of 0 to 1, thereby obtaining the second average pixel value. When the image brightness quality of the image to be scored is obtained from the normalized second average pixel value, multiplying the square of the difference between the second average pixel value and the first constant by the second constant to obtain a product; subtracting the product from the third constant to obtain the image brightness quality of the image to be scored. The values of the first constant, the second constant and the third constant can be customized by a user. The calculation formula of the image brightness quality is as follows:
where a is a first constant, b is a second constant, C is a third constant, C is a second average pixel value,is the image brightness quality.
In an application embodiment, the first constant is 0.5, the second constant b is 4, and the third constant is 1, and the calculation formula of the image brightness quality is specifically as follows:
the greater the image brightness quality, the sharper the image, so that the first average pixel value is converted into the image brightness quality for linear evaluation of the image brightness, and a lower image brightness quality value can be obtained for an excessively bright or excessively dark image. If the image to be scored is a license plate image and the unclear license plate image is filtered in traffic violation, the excessively bright or excessively dark license plate image can be rapidly removed by utilizing the brightness quality of the image.
Step S2033: based on the image brightness quality, a score corresponding to the image brightness quality is obtained.
And judging whether the value of the brightness quality of the image is larger than or equal to a preset brightness quality value. And if the value of the image brightness quality is larger than or equal to the preset brightness quality value, determining the score corresponding to the image brightness quality as a first preset value. If the value of the image brightness quality is smaller than the preset brightness quality value, the ratio of the value of the image brightness quality to the preset brightness quality value is obtained, and the score corresponding to the image brightness quality is calculated based on the ratio and the first preset value. And taking the product of the ratio and the first preset value as a fraction corresponding to the image brightness quality. The calculation formula of the score corresponding to the image brightness quality is as follows:
wherein Q_C is the fraction corresponding to the brightness quality of the image,for the image brightness quality, T is a preset brightness quality value, and d is a first preset value.
The value of the first preset value d can be customized by a user, for example, the first preset value d is 100. The value of the preset brightness quality value T is the brightness quality of the imageAny one of the values is taken.
Therefore, when the image brightness quality of the image to be scored is analyzed, all pixel values of each pixel point of the image to be scored are obtained and accumulated, and the accumulated pixel values are divided by the number of pixels, namely the first average pixel value of the image to be scored. After the first average pixel value is obtained, the first average pixel value is divided by 255 so that the first average pixel value is normalized to a range of 0 to 1, thereby obtaining a second average pixel value. Multiplying the square of the difference between the second average pixel value and the first constant by the second constant to obtain a product; and subtracting the product from the third constant to obtain the image brightness quality of the image to be scored, thereby obtaining the image brightness quality of the image to be scored based on the second average pixel value. Judging whether the value of the brightness quality of the image is larger than or equal to a preset brightness quality value; if yes, determining the score corresponding to the image brightness quality as a first preset value; if not, the ratio of the value of the image brightness quality to the preset brightness quality value is obtained, and the score corresponding to the image brightness quality is calculated based on the ratio and the first preset value.
In this embodiment, the number of image corners of the image to be scored after the graying processing is analyzed, and when the score corresponding to the brightness quality of the image is obtained, the number of corners belonging to a preset type in the image to be scored is obtained, where the preset type of the corners includes, but is not limited to, harris corners. After the number of the angular points of the image to be scored is obtained, the arctangent function value of the product of the number of the angular points and the fourth constant is obtained, the product of the fifth constant and the arctangent function value is obtained, and the minimum value in the product of the fifth constant and the arctangent function value and the second preset value is used as the score corresponding to the number of the angular points of the image. The calculation formula of the fraction of the number of image corner points is as follows:
Q_N＝min(g*arctan(f*N),e)
wherein q_n is the number of image corner points corresponding to the fraction e of the second preset value, N is the number of corner points, f is the fourth constant, and g is the fifth constant.
The spatial distribution of image corner points of the image to be scored is analyzed, and the position information is a first axis coordinate and a second axis coordinate, for example, the first axis coordinate and the second axis coordinate are an x axis and a y axis, respectively. As shown in fig. 4, fig. 4 is another flow chart of step S203 of another embodiment of the image sharpness scoring method according to the present application, specifically, step S203 includes the following steps:
step S203a: and acquiring position information of corner points belonging to a preset type in the image to be scored.
In this embodiment, harris corner points in the image to be scored are acquired, and a first axis coordinate and a second axis coordinate (x, y) of each corner point are acquired.
Step S203b: the first and second axis coordinates of each corner point are normalized.
Specifically, the formula of corner coordinate normalization is:
wherein,,for the normalized first axis coordinate, +.>For the normalized second axis coordinates, width and height are the width and length of the image to be scored, and x and y are the first axis coordinate and the second axis coordinate of each corner point.
Step S203c: obtaining a first standard deviation of the normalized first axis coordinates of the corner points, and obtaining a second standard deviation of the normalized second axis coordinates of the corner points.
Specifically, the calculation formula of the first standard deviation and the second standard deviation is as follows:
wherein N is the number of corner points,for the normalized first axis coordinate, +.>For the normalized second axis coordinate, +.>For the mean value of the normalized first axis coordinates, +.>Is the mean value of the normalized second axis coordinates. Sig (sig) x For a first standard deviation, sig y Is the second standard deviation.
Step S203d: and obtaining a mean value between the square of the first standard deviation and the square of the second standard deviation, and taking the product of the square root of the mean value and a third preset value as a score corresponding to the spatial distribution of the image corner points.
Specifically, the calculation formula of the score of the spatial distribution of the image corner points is as follows:
wherein q_d is a score of spatial distribution of image corner points, and h is a third preset value.
In an embodiment, one or more characteristics of the image brightness quality, the image corner number and the image corner spatial distribution can be selected at will for analysis to obtain corresponding scores. The first preset value, the second preset value and the third preset value can be the same, for example, the values are all 100,
step S204: and obtaining the definition score of the image to be scored by using the score of at least one feature.
And after the score of each feature is obtained, weighting and summing the scores of at least one feature to obtain the definition score of the image to be scored. When at least one feature of image brightness quality, image corner number and image corner space distribution is selected to score the definition of the image to be scored, the sum of the weights of all the selected features is 1, and the weight of each feature can be customized.
By the method, the image to be scored is obtained, the image to be scored is subjected to gray processing, at least one feature of the image to be scored after the gray processing is analyzed, the score corresponding to each feature is obtained, the score of at least one feature is utilized to obtain the definition score of the image to be scored, and the definition of the image can be scored more accurately.
In a specific application, at the evidence obtaining point of traffic violation penalty of the expressway, a license plate image of a vehicle is obtained as an image to be scored, three characteristics of image brightness quality, image corner number and image corner spatial distribution of the image to be scored are analyzed to obtain the score corresponding to each characteristic, and then the score of each characteristic is utilized to obtain the definition score of the image to be scored. The license plate image contains characters, and the corner points are generally distributed in the character parts, so that when the number of the image corner points of the license plate image is scored, the characters in the license plate image can be scored, the priori of the characters is considered, and the influence of the edge characteristics of the frame of the license plate image on the definition scoring of the license plate image is avoided. And the characters are uniformly distributed in the license plate image, so that the scoring of the spatial distribution of the image corner points is introduced, and the error of the license plate image definition scoring result caused by the aggregation of the image corner points can be reduced. Based on the method, for massive license plate images, the unclear license plate images can be rapidly filtered by using the image definition scoring method, the evidence obtaining quantity of traffic violation penalty is reduced, the method does not involve frequency domain operation of the images, the flow is relatively simple, the calculation is not complex, and therefore the processing efficiency of the license plate images can be improved.
Referring to fig. 5, fig. 5 is a schematic diagram of a frame of an electronic device according to an embodiment of the application. Specifically, the electronic device 500 in this embodiment includes a memory 510 and a processor 520 coupled to each other. Wherein the memory 510 is used for storing program instructions and data that need to be stored when processed by the processor 520.
Processor 520 controls memory 510 and itself to implement the steps of any of the embodiments of the target tracking method described above. The processor 520 may also be referred to as a CPU (Central Processing Unit ). Processor 520 may be an integrated circuit chip with signal processing capabilities. Processor 520 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 520 may be commonly implemented by a plurality of constituent circuit chips.
In an embodiment, the electronic device 500 may further include an image capturing device 530, and the processor 520 is further configured to control the image capturing device 530 to capture an image of the target scene by the image capturing device 530, so as to obtain an image containing the target. In another embodiment, the electronic apparatus 500 may not include the image capturing device 530, and the electronic apparatus 500 includes a communication circuit, and the processor 520 is connected to the external image capturing device through the communication circuit to obtain the image including the object captured by the image capturing device.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 6, the electronic device 600 includes a first acquisition module 610, an analysis module 620, and a second acquisition module 630.
The first obtaining module 610 is configured to obtain an image to be scored.
The analysis module 620 is configured to analyze at least one feature of the image to be scored to obtain a score corresponding to each feature. Wherein the at least one feature comprises at least one of image brightness quality, number of image corners and spatial distribution of image corners.
The second obtaining module 630 is configured to obtain a sharpness score of the image to be scored by using the score of the at least one feature.
Referring to fig. 7, fig. 7 is a schematic diagram illustrating a frame of a storage device 700 according to an embodiment of the application. The storage device 700 of the present application stores program instructions 701 that can be executed by a processor, where the program instructions 701 are used to implement the steps of the embodiment of the scoring method for sharpness of any of the images described above.
The storage device 700 may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other media capable of storing the program instructions 701, or may be a server storing the program instructions 701, where the server may send the stored program instructions 701 to another device for execution, or may also self-execute the stored program instructions 701.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (9)
1. A method for scoring image sharpness, comprising:
acquiring an image to be scored;
analyzing at least two features of the image to be scored to obtain a score corresponding to each feature, wherein the at least two features comprise image brightness quality and image corner number, or the at least two features comprise image brightness quality and image corner spatial distribution;
obtaining a definition score of the image to be scored by utilizing the scores of the at least two features;
the calculating step of the image brightness quality comprises the following steps:
acquiring a first average pixel value of the image to be scored;
normalizing the first average pixel value to a second average pixel value;
multiplying the square of the difference between the second average pixel value and the first constant by a second constant to obtain a product;
subtracting the product from a third constant to obtain the image brightness quality of the image to be scored;
the step of determining the fraction of the image brightness quality comprises:
judging whether the value of the brightness quality of the image is larger than or equal to a preset brightness quality value;
if yes, determining the score corresponding to the image brightness quality as a first preset value;
if not, the ratio of the value of the image brightness quality to the preset brightness quality value is obtained, and the product of the ratio and the first preset value is used as the corresponding fraction of the image brightness quality.
2. The method according to claim 1, wherein the at least two features include a number of image corner points, and the analyzing the at least two features of the image to be scored to obtain a score corresponding to each feature includes:
acquiring the number of corner points belonging to a preset type in the image to be scored;
and obtaining the score corresponding to the number of the image corner points based on the number of the corner points.
3. The method according to claim 2, wherein the obtaining, based on the number of corner points, a score corresponding to the number of corner points of the image includes:
and obtaining the arctangent function value of the product of the number of the angular points and the fourth constant, obtaining the product of the fifth constant and the arctangent function value, and taking the minimum value of the product of the fifth constant and the arctangent function value and the second preset value as the score corresponding to the number of the angular points of the image.
4. The method according to claim 1, wherein the at least two features include spatial distribution of image corner points, and the analyzing the at least two features of the image to be scored to obtain a score corresponding to each feature includes:
acquiring position information of corner points belonging to a preset type in the image to be scored;
and acquiring the score corresponding to the spatial distribution of the image corner based on the position information of the corner.
5. The method according to claim 4, wherein the position information includes a first axis coordinate and a second axis coordinate, and the obtaining the score corresponding to the spatial distribution of the image corner based on the position information of the corner includes:
normalizing the first axis coordinate and the second axis coordinate of each corner point;
acquiring a first standard deviation of the normalized first axis coordinate of the angular point, and acquiring a second standard deviation of the normalized second axis coordinate of the angular point;
and obtaining a mean value between the square of the first standard deviation and the square of the second standard deviation, and taking the product of the square root of the mean value and a third preset value as a score corresponding to the spatial distribution of the image corner points.
6. The method according to any one of claims 1 to 5, further comprising, before said analyzing at least two features of said image to be scored to obtain a score corresponding to each of said features:
graying the image to be scored;
analyzing at least two features of the image to be scored to obtain a score corresponding to each feature, including:
analyzing at least two characteristics of the image to be scored after the graying treatment to obtain the score corresponding to each characteristic;
the obtaining the sharpness score of the image to be scored by using the scores of the at least two features comprises the following steps:
and carrying out weighted summation on the scores of the at least two features to obtain the definition score of the image to be scored.
7. An electronic device comprising a memory and a processor coupled to each other;
the processor is configured to execute program instructions stored in the memory to implement the method of any one of claims 1 to 6.
8. The apparatus of claim 7, further comprising an imaging device for capturing the image to be scored.
9. A storage device storing program instructions executable by a processor for implementing the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144990.1A CN111369531B (en) | 2020-03-04 | 2020-03-04 | Image definition scoring method, device and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144990.1A CN111369531B (en) | 2020-03-04 | 2020-03-04 | Image definition scoring method, device and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111369531A CN111369531A (en) | 2020-07-03 |
| CN111369531B true CN111369531B (en) | 2023-09-01 |
Family
ID=71208583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010144990.1A Active CN111369531B (en) | 2020-03-04 | 2020-03-04 | Image definition scoring method, device and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111369531B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111859022A (en) * | 2020-07-07 | 2020-10-30 | 咪咕文化科技有限公司 | Cover generation method, electronic device and computer-readable storage medium |
| CN116643372B (en) * | 2023-07-27 | 2023-10-13 | 深圳赛陆医疗科技有限公司 | Adjustment method and device, gene sequencer and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1139486A (en) * | 1997-07-24 | 1999-02-12 | Ricoh Co Ltd | Picture quality evaluating method for image |
| KR20060111045A (en) * | 2005-04-21 | 2006-10-26 | 엘지전자 주식회사 | Method for evaluating blocking effect of image |
| CN102609939A (en) * | 2012-01-16 | 2012-07-25 | 北京航空航天大学 | TFDS (Train Coach Machine Vision Detection System) image quality evaluation method and system |
| CN102903073A (en) * | 2012-10-09 | 2013-01-30 | 深圳市掌网立体时代视讯技术有限公司 | Image definition calculating method and apparatus |
| CN103093419A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Method and device for detecting image definition |
| JP5500404B1 (en) * | 2013-05-28 | 2014-05-21 | 株式会社コンセプト | Image processing apparatus and program thereof |
| CN104182983A (en) * | 2014-08-27 | 2014-12-03 | 重庆大学 | Highway monitoring video definition detection method based on corner features |
| CN105139404A (en) * | 2015-08-31 | 2015-12-09 | 广州市幸福网络技术有限公司 | Identification camera capable of detecting photographing quality and photographing quality detecting method |
| CN105654470A (en) * | 2015-12-24 | 2016-06-08 | 小米科技有限责任公司 | Image selection method, device and system |
| WO2019033574A1 (en) * | 2017-08-17 | 2019-02-21 | 平安科技（深圳）有限公司 | Electronic device, dynamic video face recognition method and system, and storage medium |
| CN109544504A (en) * | 2018-10-16 | 2019-03-29 | 天津大学 | Screen picture quality evaluating method based on rarefaction representation |
| CN109785343A (en) * | 2019-01-17 | 2019-05-21 | 深圳英飞拓科技股份有限公司 | Face based on clarity scratches the preferred method and device of figure picture |
| CN110706183A (en) * | 2019-10-11 | 2020-01-17 | 成都极米科技股份有限公司 | Method and device for determining image definition, projector equipment and storage medium |
| CN110717922A (en) * | 2018-07-11 | 2020-01-21 | 普天信息技术有限公司 | Image definition evaluation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346792B (en) * | 2013-07-24 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Image processing method, Photo Viewer and terminal |
-
2020
- 2020-03-04 CN CN202010144990.1A patent/CN111369531B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1139486A (en) * | 1997-07-24 | 1999-02-12 | Ricoh Co Ltd | Picture quality evaluating method for image |
| KR20060111045A (en) * | 2005-04-21 | 2006-10-26 | 엘지전자 주식회사 | Method for evaluating blocking effect of image |
| CN103093419A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Method and device for detecting image definition |
| CN102609939A (en) * | 2012-01-16 | 2012-07-25 | 北京航空航天大学 | TFDS (Train Coach Machine Vision Detection System) image quality evaluation method and system |
| CN102903073A (en) * | 2012-10-09 | 2013-01-30 | 深圳市掌网立体时代视讯技术有限公司 | Image definition calculating method and apparatus |
| JP5500404B1 (en) * | 2013-05-28 | 2014-05-21 | 株式会社コンセプト | Image processing apparatus and program thereof |
| CN104182983A (en) * | 2014-08-27 | 2014-12-03 | 重庆大学 | Highway monitoring video definition detection method based on corner features |
| CN105139404A (en) * | 2015-08-31 | 2015-12-09 | 广州市幸福网络技术有限公司 | Identification camera capable of detecting photographing quality and photographing quality detecting method |
| CN105654470A (en) * | 2015-12-24 | 2016-06-08 | 小米科技有限责任公司 | Image selection method, device and system |
| WO2019033574A1 (en) * | 2017-08-17 | 2019-02-21 | 平安科技（深圳）有限公司 | Electronic device, dynamic video face recognition method and system, and storage medium |
| CN110717922A (en) * | 2018-07-11 | 2020-01-21 | 普天信息技术有限公司 | Image definition evaluation method and device |
| CN109544504A (en) * | 2018-10-16 | 2019-03-29 | 天津大学 | Screen picture quality evaluating method based on rarefaction representation |
| CN109785343A (en) * | 2019-01-17 | 2019-05-21 | 深圳英飞拓科技股份有限公司 | Face based on clarity scratches the preferred method and device of figure picture |
| CN110706183A (en) * | 2019-10-11 | 2020-01-17 | 成都极米科技股份有限公司 | Method and device for determining image definition, projector equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于轮廓曲率的多边形角点检测算法;王秋燕;《测绘》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111369531A (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852997B (en) | Dynamic image definition detection method and device, electronic equipment and storage medium | |
| CN113240630B (en) | Speckle image quality evaluation method and device, terminal equipment and readable storage medium | |
| JP2023503749A (en) | CAMERA LENS STATE DETECTION METHOD, DEVICE, DEVICE, AND STORAGE MEDIUM | |
| CN111369531B (en) | Image definition scoring method, device and storage device | |
| CN111445058B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN111368587B (en) | Scene detection method, device, terminal equipment and computer readable storage medium | |
| CN109903265B (en) | Method and system for setting detection threshold value of image change area and electronic device thereof | |
| CN114724000B (en) | Screen shot image moire processing method, device and equipment | |
| CN116129195A (en) | Image quality evaluation device, image quality evaluation method, electronic device, and storage medium | |
| CN112836726B (en) | Pointer instrument indication reading method and device based on video information | |
| CN111222446B (en) | Face recognition method, face recognition device and mobile terminal | |
| CN111524153B (en) | Image analysis force determination method and device and computer storage medium | |
| CN111311610A (en) | Image segmentation method and terminal equipment | |
| CN115690747B (en) | Vehicle blind area detection model test method and device, electronic equipment and storage medium | |
| CN111539975A (en) | Method, device and equipment for detecting moving target and storage medium | |
| US20060126136A1 (en) | Image inspecting apparatus, image inspecting method, control program and computer-readable storage medium | |
| CN111445435A (en) | No-reference image quality evaluation method based on multi-block wavelet transform | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN111027560B (en) | Text detection method and related device | |
| Saad et al. | Natural DCT statistics approach to no-reference image quality assessment | |
| CN114663681A (en) | Method for reading pointer type meter and related product | |
| CN115965776A (en) | SFR (Small form-factor rating) graph card identification method and device, electronic equipment and storage medium | |
| CN112614100A (en) | Ocean plankton image segmentation method | |
| CN112785550A (en) | Image quality value determination method, image quality value determination device, storage medium, and electronic device | |
| CN112017163B (en) | Image ambiguity detection method, device, electronic equipment and storage medium |
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 |