A method, apparatus, system and storage medium for image automated testing

Abstract

The application provides a kind of image automatic test method, device, system and storage medium, including the image frame of test card adopts MTF-edge method to calculate the restoration ability of camera to edge, the mean value of each frequency of edge region is output as the definition of the image frame of the test card, whether it is qualified according to the definition;The image frame of the whiteboard is converted into gray scale image and is carried out after fuzzy noise reduction processing, binarization, erosion inflation, connected domain extraction and connected domain filtering, according to the difference of the lowest gray value of the region compared with the gray value of the surrounding background region, determine the black dot that exists in the filtered connected domain, and whether it is qualified according to the pixel value size of black dot;The proportion of the number of abnormal pixels in the image frame of the whiteboard accounts for the four corner regions, whether it is qualified according to the proportion. Using the above technical scheme, the space of test in production process can be greatly saved, the speed and efficiency of image detection are improved, and the stability of test result is improved.

Description

Technical Field

[0001] This invention relates to the field of image testing, and in particular to a method, apparatus, system, and storage medium for automated image testing. Background Technology

[0002] Currently, image testing presents significant challenges in actual production, with the main pain points and drawbacks being as follows:

[0003] 1. The testing environment is limited. Traditional image testing and judgment, such as sharpness testing, black border testing, and black spot testing, require a certain distance and space requirements. Among them, sharpness testing requires a distance of at least three meters.

[0004] 2. Extensive testing: To improve testing speed, test cards are widely distributed throughout the production environment. Production relies on quantity to improve quality, resulting in a significant investment of manpower for testing.

[0005] 3. Image judgment consistency: Different personnel have different sensitivities to images, resulting in different judgment results and inconsistent final outputs.

[0006] 4. When problems occur in routine image production, personnel need to register and describe the specific issues, which requires a significant amount of effort to compile statistics. Summary of the Invention

[0007] Embodiments of the present invention provide a method, apparatus, system, and storage medium for automated image testing to improve the speed and efficiency of image detection.

[0008] To achieve the above objectives, on the one hand, a method for automated image testing is provided, specifically including:

[0009] Sharpness test: The test card is photographed on a panel fixed at a predetermined distance to obtain the image frame of the test card. The MTF-edge method is used on the image frame of the test card to calculate the camera's ability to reproduce the edge. The average value of each frequency in the edge area is output as the sharpness of the image frame of the test card. The image frame of the test card is judged to be qualified based on the sharpness.

[0010] Black spot test: Capture an image frame of the white board, convert the image frame of the white board into a grayscale image and perform blur and noise reduction processing, then perform binarization, erosion and dilation, connected component extraction and connected component filtering, and output the filtered connected component. The difference between the lowest grayscale value of the region and the grayscale value of the surrounding background region is used as the conspicuousness. Based on the conspicuousness, black spots existing in the filtered connected component are determined, and the image frame of the white board is judged to be qualified based on the pixel value of the black spots.

[0011] Black border test: Calculate the proportion of abnormal pixels in the four corner areas of the image frame of the whiteboard, and determine whether the image frame of the whiteboard is qualified based on the proportion.

[0012] In a specific embodiment, the sharpness test specifically includes:

[0013] The edge position of the image frame of the test card is determined by the MTF-edge method. After the region where the edge is located is cropped and the image is differentially analyzed, a fast Fourier transform is performed to obtain a spectrum. The mean value of each frequency is obtained from the spectrum as the sharpness of the image frame of the test card.

[0014] When the clarity is lower than a preset clarity threshold, the image frame of the test card is determined to be an unqualified image.

[0015] In a specific embodiment, the black spot test specifically includes:

[0016] After converting the image frame of the whiteboard into a grayscale image and performing blur and noise reduction processing, binarization, erosion and dilation, and connected component extraction are performed between threshold regions to obtain several connected components.

[0017] Filter out connected components and background that are smaller than the preset filtering threshold, and output the filtered connected components.

[0018] The difference between the lowest gray value of a region and the gray value of the surrounding background region is used as the saliency. Connected regions in the filtered connected regions with saliency higher than a preset saliency threshold are considered black points. If there are black points in the image frame and the pixel value of the black points is greater than a preset pixel threshold, then the image frame of the whiteboard is an unqualified image.

[0019] In a specific embodiment, the step of obtaining the average value of each frequency based on the spectrum as the image frame sharpness of the test card specifically includes:

[0020] Find the highest response value among the intensity responses at each frequency in the spectrum graph;

[0021] The mean value is obtained by dividing the area formed by the intensity of each frequency in the spectrum and the coordinate axis by the area of ​​the rectangle formed by the highest response value and the coordinate axis over the entire frequency band.

[0022] In a specific embodiment, the black border test specifically includes:

[0023] A preset brightness threshold is set, and pixels with grayscale values ​​lower than the brightness threshold are considered abnormal pixels. The proportion of the number of abnormal pixels in the four corner areas is calculated. When the proportion is higher than a preset proportion threshold, the image frame of the whiteboard is a defective image.

[0024] In a specific embodiment, the whiteboard is a transmissive whiteboard.

[0025] In a specific embodiment, the equipment used for shooting and the corresponding connection positions specifically include: a test box, a camera, a teleconverter, a test card, and auxiliary devices;

[0026] The auxiliary device includes a rotating platform and a clamp;

[0027] The parameters of the teleconverter are defined based on the requirement that the simulated distance is greater than 5m, and the distance between the camera and the teleconverter, as well as the distance between the test card and the teleconverter, are designed.

[0028] The camera is secured by a custom-designed clamp;

[0029] The test card is a chessboard card.

[0030] On the other hand, a system for automated image testing is provided, comprising:

[0031] Sharpness testing module: Configured to capture image frames of a test card fixed on a panel at a predetermined distance. The MTF-edge method is used on the image frames of the test card to calculate the camera's ability to reproduce the edge. The average value of each frequency in the edge region is output as the sharpness of the image frames of the test card. The image frames of the test card are judged to be qualified based on the sharpness.

[0032] Black spot testing module: Configured to capture image frames of a whiteboard, convert the image frames of the whiteboard into grayscale images and perform blur and noise reduction processing, then perform binarization, erosion and dilation, connected component extraction and connected component filtering, output the filtered connected components, use the difference between the lowest grayscale value of the region and the grayscale value of the surrounding background region as the conspicuousness, determine the black spots existing in the filtered connected components based on the conspicuousness, and judge whether the image frame of the whiteboard is qualified based on the pixel value of the black spots.

[0033] Black border test module: configured to count the proportion of abnormal pixels in the four corner areas of the image frame of the whiteboard, and determine whether the image frame of the whiteboard is qualified based on the proportion.

[0034] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a computer processor, performs the method for automated image testing as described above.

[0035] In another aspect, an apparatus for automated image testing is provided, comprising a memory and a processor, the memory storing at least one program, the at least one program being executed by the processor to implement the method for automated image testing as described above.

[0036] The above technical solution has the following technical effects:

[0037] 1. Using teleconverters to simulate different actual distances as the testing environment can greatly save testing space during the production process;

[0038] 2. The software automatically judges the image, requiring only one person to place the camera inside and perform a one-click test, saving a lot of labor costs. It is also faster and more accurate than manual judgment, improving the speed and efficiency of image detection.

[0039] 3. A checkerboard pattern was selected as the test card for the sharpness test. A transmissive white board was used for the black dots and black edges. The sharpness was calculated using MTF. The test card position and light source were fixed to ensure stable test results.

[0040] 4. Automatically record and save problem images in a specific path. The program can search for relevant information and retrieve the records. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating an embodiment of an automated image testing method according to the present invention;

[0042] Figure 2 This is a schematic diagram of blade edge selection for automated image testing according to another embodiment of the present invention;

[0043] Figure 3 This invention provides an MTF differential image for automated image testing, as another embodiment of the present invention.

[0044] Figure 4 This is another embodiment of the present invention, showing an MTF spectrum diagram for automated image testing;

[0045] Figure 5 This is a flowchart of black spot processing for automated image testing according to another embodiment of the present invention;

[0046] Figure 6 This is a grayscale image for black dot testing, as described in another embodiment of the present invention;

[0047] Figure 7 This is an image showing the erosion and dilation processing result of black spot testing in an embodiment of the present invention for automated image testing.

[0048] Figure 8 This is a filtered connected component graph for automated image testing according to another embodiment of the present invention;

[0049] Figure 9 This is a black dot image from an embodiment of the present invention for automated image testing;

[0050] Figure 10This is a black dot image with a saliency of 1 for an automated image testing method, according to another embodiment of the present invention.

[0051] Figure 11 This is a black dot image with a saliency of 4 for an automated image testing method according to another embodiment of the present invention.

[0052] Figure 12 This is a black dot image with a saturation of 10 for an automated image testing method, according to another embodiment of the present invention.

[0053] Figure 13 This is a schematic diagram of the structure of the automated image testing device according to an embodiment of the present invention. Detailed Implementation

[0054] To further illustrate the various embodiments, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, primarily used to illustrate the embodiments and to explain the operating principles of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these drawings, those skilled in the art should be able to understand other possible implementations and the advantages of the present invention. Components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0055] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0056] Example 1:

[0057] Figure 1 This is a schematic flowchart illustrating an automated image testing method according to an embodiment of the present invention. In this embodiment,

[0058] Sharpness test: The test card is photographed on a panel fixed at a predetermined distance to obtain the image frame of the test card. The MTF-edge method is used on the image frame of the test card to calculate the camera's ability to reproduce the edge. The average value of each frequency in the edge area is output as the sharpness of the image frame of the test card. The image frame of the test card is judged to be qualified based on the sharpness.

[0059] Black spot test: Capture an image frame of the white board, convert the image frame of the white board into a grayscale image and perform blur and noise reduction processing, then perform binarization, erosion and dilation, connected component extraction and connected component filtering, and output the filtered connected component. The difference between the lowest grayscale value of the region and the grayscale value of the surrounding background region is used as the conspicuousness. Based on the conspicuousness, black spots existing in the filtered connected component are determined, and the image frame of the white board is judged to be qualified based on the pixel value of the black spots.

[0060] Black border test: Calculate the proportion of abnormal pixels in the four corner areas of the image frame of the whiteboard, and determine whether the image frame of the whiteboard is qualified based on the proportion.

[0061] Example 2:

[0062] The equipment used for automated image testing in this invention includes:

[0063] The whiteboard is a transmissive whiteboard.

[0064] The equipment used for shooting and the corresponding connection points specifically include: test box, camera, teleconverter, test card, and auxiliary devices;

[0065] The auxiliary device includes a rotating platform and a clamp;

[0066] The parameters of the teleconverter are defined based on the requirement that the simulated distance is greater than 5m, and the distance between the camera and the teleconverter, as well as the distance between the test card and the teleconverter, are designed.

[0067] The camera is secured by a custom-designed clamp;

[0068] The test card is a chessboard card.

[0069] When performing automated image testing:

[0070] Different cameras are fixed in place by custom clamps to photograph chessboard cards fixed at a certain distance on a panel. Sharpness data is obtained through a sharpness test method. The camera is then rotated to the white board on the other side via a rotating platform, and the distance is increased to cover the entire screen area. Black dot and black edge data are obtained through black dot and black edge tests. The sharpness data and the black dot and black edge data are used to determine whether the captured image is up to standard.

[0071] Example 3:

[0072] In a specific embodiment, the sharpness test steps are as follows:

[0073] Figure 2 This is a schematic diagram of the edge selection for automated image testing according to another embodiment of the present invention. The edge position of the image frame of the test card is determined by the MTF-edge method.

[0074] Figure 3 In another embodiment of the present invention, an MTF differential image for automated image testing is obtained by cropping the region where the blade edge is located, performing image difference, and then performing a fast Fourier transform to obtain a spectrum.

[0075] Figure 4 This is another embodiment of the present invention, showing an MTF spectrum for automated image testing, based on... Figure 4 Find the highest response value among the intensity responses at each frequency in the spectrum graph;

[0076] Then, divide the area formed by the intensity of each frequency in the spectrum and the coordinate axis by the area of ​​the rectangle formed by the highest response value and the coordinate axis over the entire frequency band (i.e., the area of ​​the rectangle in the figure) to obtain the mean value.

[0077] When the clarity is lower than a preset clarity threshold, the image frame of the test card is determined to be an unqualified image.

[0078] Example 4:

[0079] The imaging characteristics of black dots in IPC are as follows: According to the black dot image sample, the black dots in the image are randomly distributed; and their shapes are not fixed, mainly circular, accompanied by a few long strips or bands of black areas. That is, a dark black area that can be seen with the naked eye.

[0080] The brightness distribution of IPC against a pure white background is as follows: it is generally bright in the center and becomes darker the farther away from the center. When converted to grayscale, the seemingly smooth white background is actually fluctuating and has obvious noise effects.

[0081] Based on the above characteristics Figure 5 This is a flowchart of black spot processing for automated image testing according to another embodiment of the present invention, as shown below. Figure 5 The test steps for the black dots shown are as follows:

[0082] Figure 6 In another embodiment of the present invention, a grayscale image for black spot testing of an automated image test is generated by converting the image frame of the white board into a grayscale image and performing blur and noise reduction processing.

[0083] Binarization between threshold regions generates 255 binarized images, followed by erosion, dilation, and connected component extraction to obtain several connected components. Figure 7 This is a result of black spot erosion and dilation processing in an embodiment of the present invention for automated image testing. The binarization threshold used in the figure is 158.

[0084] Based on a preset filtering threshold, connected components and background data smaller than the threshold are filtered out, and the filtered connected components are output, such as... Figure 8 As shown; Figure 8 This is a filtered connected component graph for automated image testing according to another embodiment of the present invention;

[0085] Figure 9 This is a black dot image for automated image testing according to an embodiment of the present invention, wherein the boxed area represents a black dot;

[0086] The difference between the lowest gray value of a region and the gray value of the surrounding background region is used as the salience. Connected regions in the filtered connected regions with a salience higher than a preset salience threshold are used as black dots.

[0087] Based on the above embodiments, the following is obtained: Figures 10-12 , Figures 10-12 The images show black dots with a visibility threshold of 1, 4, and 10, respectively. Generally, when the visibility threshold is greater than 2 pixels, the human eye can distinguish them with careful observation, and when the visibility threshold is greater than 4 pixels, the human eye can usually see them at a glance. Therefore, in this embodiment, the visibility threshold is set to 2.

[0088] If a black dot exists in the image frame and the pixel value of the black dot is greater than a preset pixel threshold, then the image frame of the whiteboard is a defective image.

[0089] Example 5:

[0090] The black border test steps are as follows:

[0091] A preset brightness threshold is used. Pixels with grayscale values ​​lower than the brightness threshold are considered abnormal pixels. The proportion of abnormal pixels in the four corner areas is calculated. When the proportion is higher than a preset proportion threshold, the image frame of the whiteboard is considered an unqualified image. The proportion of abnormal pixels in the four corner areas is calculated as: number of abnormal pixels / (image width / 16 * image height / 16), and the brightness threshold is set to 50.

[0092] Example 6:

[0093] The present invention also provides a (device), such as Figure 13 As shown, the device includes a processor 1301, a memory 1302, a bus 1303, and a computer program stored in the memory 1302 and executable on the processor 1301. The processor 1301 includes one or more processing cores. The memory 1302 is connected to the processor 1301 via the bus 1303. The memory 1302 is used to store program instructions. When the processor executes the computer program, it implements the steps in the above-described method embodiment of Embodiment 1 of the present invention.

[0094] Furthermore, as an executable solution, the (device) can be a computer unit, which may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer unit may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above-described structure of the computer unit is merely an example and does not constitute a limitation on the computer unit. It may include more or fewer components, or combine certain components, or use different components. For example, the computer unit may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.

[0095] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, connecting various parts of the entire computer unit via various interfaces and lines.

[0096] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the computer unit by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0097] Example 7:

[0098] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.

[0099] If the modules / units integrated in the computer unit are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0100] Although the invention has been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the invention without departing from the spirit and scope of the invention as defined in the appended claims, all of which shall be within the scope of protection of the invention.

Claims

1. A method for automated image testing, specifically including: Sharpness test: The test card is photographed on a panel fixed at a predetermined distance to obtain the image frame of the test card. The MTF-edge method is used on the image frame of the test card to calculate the camera's ability to reproduce the edge. The average value of each frequency in the edge area is output as the sharpness of the image frame of the test card. The image frame of the test card is judged to be qualified based on the sharpness. Black spot test: Capture an image frame of the white board, convert the image frame of the white board into a grayscale image and perform blur and noise reduction processing, then perform binarization, erosion and dilation, connected component extraction and connected component filtering, and output the filtered connected component. The difference between the lowest grayscale value of the region and the grayscale value of the surrounding background region is used as the conspicuousness. Based on the conspicuousness, black spots existing in the filtered connected component are determined, and the image frame of the white board is judged to be qualified based on the pixel value of the black spots. Black border test: Calculate the proportion of abnormal pixels in the four corner areas of the image frame of the whiteboard, and determine whether the image frame of the whiteboard is qualified based on the proportion; The equipment used for shooting and the corresponding connection points specifically include: test box, camera, teleconverter, test card, and auxiliary devices; The auxiliary device includes a rotating platform and a clamp; The parameters of the teleconverter are defined based on the requirement that the simulated distance is greater than 5m, and the distance between the camera and the teleconverter, as well as the distance between the test card and the teleconverter, are designed. The camera is secured by a custom-designed clamp; The test card is a chessboard card.

2. The method according to claim 1, characterized in that, The clarity test specifically includes: The edge position of the image frame of the test card is determined by the MTF-edge method. After the region where the edge is located is cropped and the image is differentially analyzed, a fast Fourier transform is performed to obtain a spectrum. The mean value of each frequency is obtained from the spectrum as the sharpness of the image frame of the test card. When the clarity is lower than a preset clarity threshold, the image frame of the test card is determined to be an unqualified image.

3. The method according to claim 1, characterized in that, The black spot test specifically includes: After converting the image frame of the whiteboard into a grayscale image and performing blur and noise reduction processing, binarization, erosion and dilation, and connected component extraction are performed between threshold regions to obtain several connected components. Filter out connected components and background that are smaller than the preset filtering threshold, and output the filtered connected components. The difference between the lowest gray value of a region and the gray value of the surrounding background region is used as the saliency. Connected regions in the filtered connected regions with saliency higher than a preset saliency threshold are considered black points. If there are black points in the image frame and the pixel value of the black points is greater than a preset pixel threshold, then the image frame of the whiteboard is an unqualified image.

4. The method according to claim 2, characterized in that, The step of using the average value of each frequency obtained from the spectrogram as the image frame sharpness of the test card specifically includes: Find the highest response value among the intensity responses at each frequency in the spectrum graph; The mean value is obtained by dividing the area formed by the intensity of each frequency in the spectrum and the coordinate axis by the area of ​​the rectangle formed by the highest response value and the coordinate axis over the entire frequency band.

5. The method according to claim 1, characterized in that, The black border test specifically includes: A preset brightness threshold is set, and pixels with grayscale values ​​lower than the brightness threshold are considered abnormal pixels. The proportion of the number of abnormal pixels in the four corner areas is calculated. When the proportion is higher than a preset proportion threshold, the image frame of the whiteboard is a defective image.

6. The method according to claim 1, characterized in that, The whiteboard is a transmissive whiteboard.

7. A system for automated image testing, comprising: Sharpness testing module: Configured to capture image frames of a test card fixed on a panel at a predetermined distance. The MTF-edge method is used on the image frames of the test card to calculate the camera's ability to reproduce the edge. The average value of each frequency in the edge region is output as the sharpness of the image frames of the test card. The image frames of the test card are judged to be qualified based on the sharpness. The equipment used for shooting and the corresponding connection points specifically include: test box, camera, teleconverter, test card, and auxiliary devices; The auxiliary device includes a rotating platform and a clamp; The parameters of the teleconverter are defined based on the requirement that the simulated distance is greater than 5m, and the distance between the camera and the teleconverter, as well as the distance between the test card and the teleconverter, are designed. The camera is secured by a custom-designed clamp; The test card is a chessboard card; Black spot testing module: Configured to capture image frames of a whiteboard, convert the image frames of the whiteboard into grayscale images and perform blur and noise reduction processing, then perform binarization, erosion and dilation, connected component extraction and connected component filtering, output the filtered connected components, use the difference between the lowest grayscale value of the region and the grayscale value of the surrounding background region as the conspicuousness, determine the black spots existing in the filtered connected components based on the conspicuousness, and judge whether the image frame of the whiteboard is qualified based on the pixel value of the black spots. Black border test module: configured to count the proportion of abnormal pixels in the four corner areas of the image frame of the whiteboard, and determine whether the image frame of the whiteboard is qualified based on the proportion.

8. An apparatus for automated image testing, characterized in that, The system includes a memory and a processor, the memory storing at least one program, which is executed by the processor to implement the method for automated image testing as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one program, which is executed by a processor to implement the method for automated image testing as described in any one of claims 1 to 6.

Images