Image quality inspection method and device based on recycling detection

Abstract

This invention relates to an image quality inspection method and apparatus based on recycling detection. After acquiring an appearance image of the equipment to be recycled, the appearance image undergoes color space conversion processing to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, the appearance image is determined to be qualified by comparing each image quality parameter with a preset parameter threshold; wherein qualified appearance images are used for recycling detection. Based on this, by pre-comparing the image quality parameters, unqualified appearance images are eliminated, and qualified appearance images are retained for recycling detection, thereby improving the efficiency and accuracy of recycling detection.

Description

Technical Field

[0001] This invention relates to the field of recycling detection technology, and in particular to an image quality inspection method and apparatus based on recycling detection. Background Technology

[0002] With the development of electronic product technology, various smart devices are emerging in an endless stream, such as smartphones, laptops, and tablets. Currently, along with rapid economic and technological development, the popularization and upgrading speed of smart devices are also accelerating. Taking smartphones as an example, the arrival of the 5G era has accelerated the replacement of smartphones. In the process of smart device iteration, effective recycling is one of the effective means of utilizing the residual value of smart devices, which can reduce chemical pollution to the environment and reduce waste.

[0003] Therefore, along with the equipment recycling process, various recycling methods have emerged, with the most common being recycling machines. These machines require visual inspection during recycling, typically using cameras to capture images of the smart device's exterior. However, the environments in which these machines capture these images are complex and diverse, including enclosed, semi-enclosed, and open environments. This means the captured images are susceptible to varying degrees of interference, affecting the accuracy of the recycling inspection. Furthermore, if the recycling inspection server uses these images as training samples, it increases the data processing load, reducing training efficiency and accuracy.

[0004] In summary, it is evident that traditional recycling inspection methods still have the above-mentioned shortcomings in data detection based on appearance images. Summary of the Invention

[0005] Therefore, it is necessary to address the complex and diverse environments in which recycling machines collect appearance images, including closed, semi-closed, and open environments. These environments can cause varying degrees of interference to the collected appearance images, affecting the accuracy of recycling detection. Furthermore, if the recycling detection execution server uses appearance images as training samples, it will increase the data processing load and reduce the efficiency and accuracy of training. To address these shortcomings, an image quality inspection method and device based on recycling detection should be provided.

[0006] An image quality inspection method based on recycling detection includes the following steps:

[0007] Obtain an external image of the equipment to be recycled;

[0008] The appearance image is subjected to color space conversion processing to generate a corresponding grayscale image;

[0009] The grayscale image is divided into regions to obtain region images;

[0010] Calculate the image quality parameters of the region image;

[0011] The appearance image is determined to be qualified by comparing each of the image quality parameters with a preset parameter threshold; wherein, the qualified appearance image is used for recycling detection.

[0012] The aforementioned image quality inspection method based on recycling detection, after acquiring the appearance image of the equipment to be recycled, performs color space conversion processing on the appearance image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, the appearance image is determined to be qualified by comparing each image quality parameter with a preset threshold; qualified appearance images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified appearance images are discarded, and qualified appearance images are retained for recycling detection, improving the efficiency and accuracy of recycling detection.

[0013] In one embodiment, before the process of dividing the grayscale image into regions to obtain region images, the method further includes the following step:

[0014] The grayscale image is subjected to Gaussian blurring.

[0015] In one embodiment, the process of performing Gaussian blur processing on the grayscale image is as follows:

[0016]

[0017] Where G1(j,i) represents the grayscale image before Gaussian blurring, G2(j,i) represents the grayscale image after Gaussian blurring, j = 1, 2...H, i = 1, 2...W, j represents the horizontal coordinate value relative to the origin at the top left corner of the grayscale image, i represents the vertical coordinate value relative to the origin at the top left corner of the grayscale image, H represents the height of the grayscale image, W represents the width of the grayscale image, w represents the length of the rectangular window, set to 3, and A represents the amplitude of the corresponding rectangular window, set to 16; the rectangular window represents the template corresponding to the Gaussian filter, as shown in the following formula:

[0018]

[0019] In one embodiment, the process of performing color space conversion on the appearance image to generate a corresponding grayscale image is as follows:

[0020] G1(j,i)=0.1140*X1 b (j,i)+0.5870*X1 g (j,i)+0.2989*X1 r (j,i)

[0021] Where G1(j,i) represents the grayscale image, X1 r (j,i),X1 g (j,i) and X1 b (j,i) represent the color components of the R, G, and B channels of the appearance image X1(j,i), respectively.

[0022] In one embodiment, the process of dividing the grayscale image into regions to obtain region images includes the following steps:

[0023] Two or more rectangular regions are divided into the grayscale image to obtain the region image.

[0024] In one embodiment, the process of determining whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold includes the following steps:

[0025] Based on the comparison of each of the image quality parameters with the preset parameter threshold, it is determined whether the image of the region is unqualified;

[0026] The appearance image is deemed acceptable based on the number of non-compliant areas.

[0027] In one embodiment, the image quality parameters include the region mean and the region variance; the preset parameter threshold includes a preset mean threshold and a preset variance threshold;

[0028] The process of determining whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold includes the following steps:

[0029] If the mean value of a region in the image is less than a preset mean threshold, perform the first counting.

[0030] If the regional variance of a region image is less than a preset variance threshold, perform a second counting;

[0031] When the sum of the first count and the second count is less than the preset state count, the region image is determined to be unqualified;

[0032] If the number of unqualified area images exceeds a preset number, the appearance image is determined to be unqualified.

[0033] An image quality inspection device based on recycling detection, comprising:

[0034] Image acquisition module, used to acquire external images of the equipment to be recycled;

[0035] The image conversion module is used to perform color space conversion processing on the appearance image to generate a corresponding grayscale image;

[0036] An image segmentation module is used to divide the grayscale image into regions to obtain region images;

[0037] The parameter calculation module is used to calculate the image quality parameters of the region image;

[0038] The image detection module is used to determine whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold; wherein, the qualified appearance image is used for recycling detection.

[0039] The aforementioned image quality inspection device based on recycling detection, after acquiring the appearance image of the equipment to be recycled, performs color space conversion processing on the appearance image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, based on a comparison of each image quality parameter with preset parameter thresholds, the device determines whether the appearance image is qualified; qualified appearance images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified appearance images are discarded, and qualified appearance images are retained for recycling detection, improving the efficiency and accuracy of recycling detection.

[0040] A computer storage medium storing computer instructions thereon, wherein the computer instructions, when executed by a processor, implement the image quality inspection method based on recycling detection according to any of the above embodiments.

[0041] The aforementioned computer storage medium, after acquiring the appearance image of the device to be recycled, performs color space conversion processing on the appearance image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, based on a comparison of each image quality parameter with preset threshold values, the applicability of the appearance image is determined; qualified appearance images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified appearance images are discarded, and qualified appearance images are retained for recycling detection, improving the efficiency and accuracy of recycling detection.

[0042] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the image quality inspection method based on recycling detection according to any of the above embodiments.

[0043] The aforementioned computer equipment, after acquiring an image of the device to be recycled, performs color space conversion on the image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters for each region image are calculated. Finally, the applicability of the image is determined by comparing each image quality parameter with a preset threshold; qualified images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified images are removed, and qualified images are retained for recycling detection, improving the efficiency and accuracy of recycling detection. Attached Figure Description

[0044] Figure 1 A flowchart of an image quality inspection method based on recycling detection as one embodiment;

[0045] Figure 2 Flowchart of an image quality inspection method based on recycling detection, as an embodiment of another implementation;

[0046] Figure 3 This is a diagram illustrating the regional division.

[0047] Figure 4 This is a flowchart illustrating the parameter comparison process in one embodiment.

[0048] Figure 5 A structural diagram of an image quality inspection device module based on recycling detection according to one embodiment;

[0049] Figure 6 This is a schematic diagram of the internal structure of a computer according to one embodiment. Detailed Implementation

[0050] To better understand the purpose, technical solution, and technical effects of this invention, the invention will be further explained and described below in conjunction with the accompanying drawings and embodiments. It should also be stated that the embodiments described below are only for explaining this invention and are not intended to limit this invention.

[0051] The image quality inspection method based on recycling detection in this embodiment can be applied to various recycling inspections, including inspections of fixed recycling machines, handheld recycling machines, or self-testing of recycling machines by users. In all types of recycling inspections, as long as there is a camera and supplementary lighting equipment, the image quality inspection method based on recycling detection in this embodiment can control the host computer of the supplementary lighting equipment by issuing control commands. Therefore, the executing entity of the image quality inspection method based on recycling detection in this embodiment can be a cloud server, a recycling machine, or a third-party smart device; the recycling machine is only the final target. It should be noted that recycling machines include various traditional server-side applications as well as user-owned devices, such as smartphones.

[0052] Based on this, embodiments of the present invention provide an image quality inspection method based on recycling detection.

[0053] Figure 1 Here is a flowchart of an image quality inspection method based on recycling detection as one embodiment, such as Figure 1 As shown, one embodiment of the image quality inspection method based on recycling detection includes steps S100 to S104:

[0054] S100: Obtain an external image of the equipment to be recycled;

[0055] S101, Perform color space conversion processing on the appearance image to generate a corresponding grayscale image;

[0056] S102, Divide the grayscale image into regions to obtain region images;

[0057] S103, Calculate the image quality parameters of the region image;

[0058] S104, based on the comparison of each of the image quality parameters with the preset parameter threshold, determine whether the appearance image is qualified; wherein, the qualified appearance image is used for recycling detection.

[0059] The equipment to be recycled is the object of the recycling machine's recycling inspection. Typically, the recycling machine's camera takes a picture of the equipment to be recycled, obtaining an image of its appearance. The entity executing step S100 can obtain the appearance image from the recycling machine or a third-party server.

[0060] In one embodiment, Figure 2 A flowchart of another embodiment of an image quality inspection method based on recycling detection is shown below. Figure 2 As shown, before the process of dividing the grayscale image into regions and obtaining the region image in step S102, step S200 is also included:

[0061] S200, Gaussian blur processing is applied to the grayscale image.

[0062] Among them, Gaussian blurring is used to remove white noise from the appearance image.

[0063] In one embodiment, the process of performing Gaussian blur processing on the grayscale image in step S200 is as follows:

[0064]

[0065] Where G1(j,i) represents the grayscale image before Gaussian blurring, G2(j,i) represents the grayscale image after Gaussian blurring, j = 1, 2...H, i = 1, 2...W, j represents the horizontal coordinate value relative to the origin at the top left corner of the grayscale image, i represents the vertical coordinate value relative to the origin at the top left corner of the grayscale image, H represents the height of the grayscale image, W represents the width of the grayscale image, w represents the length of the rectangular window, set to 3, and A represents the amplitude of the corresponding rectangular window, set to 16; the rectangular window represents the template corresponding to the Gaussian filter, as shown in the following formula:

[0066]

[0067] In one embodiment, the process of performing color space conversion on the appearance image in step S101 to generate the corresponding grayscale image is as follows:

[0068] G1(j,i)=0.1140*X1 b (j,i)+0.5870*X1 g (j,i)+0.2989*X1 r (j,i)

[0069] Where G1(j,i) represents the grayscale image, X1 r (j,i),X1 g (j,i) and X1 b (j,i) represent the color components of the R, G, and B channels of the appearance image X1(j,i), respectively.

[0070] A corresponding grayscale image is generated through color space conversion. The parameter settings in the above formula are designed to adapt to image processing in natural scenes.

[0071] The grayscale image is divided into multiple regions, each existing independently as a region image. The quality parameters of each region image are compared with preset threshold parameters to determine whether the appearance image is acceptable; acceptable appearance images are retained for recycling detection.

[0072] The division of regions reduces the computational load for overall grayscale image brightness recognition, facilitates rapid adjustment of supplementary lighting, and is suitable for retrieval machines with only lightweight computing capabilities, thus reducing the computational burden on the method. Simultaneously, adjusting the number of regions helps improve detection accuracy.

[0073] In one embodiment, the process of dividing the grayscale image into regions and obtaining region images in step S102 includes step S300:

[0074] S300, divide the grayscale image into two or more rectangular regions to obtain the region image.

[0075] It is important to note that the region can be a regular region, such as a circle or rectangle, or an irregular region. Using a rectangular region facilitates the subsequent calculation of image quality parameters.

[0076] In one embodiment, Figure 3 This is a diagram illustrating the regional division, such as... Figure 3 As shown, the grayscale image is divided into 5 regions of the same size, located at the top left corner R1, the top right corner R2, the center R3, the bottom left corner R4, and the bottom right corner R5.

[0077] The more regions of the image that are divided, the higher the accuracy of the image quality inspection.

[0078] In one embodiment, such as Figure 2 As shown, step S104, which determines whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold, includes steps S400 and S401:

[0079] S400, based on the comparison of each of the image quality parameters with the preset parameter threshold, determine whether the region image is unqualified;

[0080] S401, determine whether the appearance image is acceptable based on the number of unacceptable area images.

[0081] Specifically, if the number of non-compliant area images exceeds a certain threshold, the appearance image is deemed non-compliant. This threshold is positively correlated with the number of area image divisions. The number of area image divisions, the predetermined number for comparison, can be flexibly adjusted based on the load capacity of the subsequent server or computing equipment, thereby adjusting the detection granularity of the image quality inspection.

[0082] In one embodiment, the image quality parameters include the region mean and the region variance; the preset parameter threshold includes a preset mean threshold and a preset variance threshold. Figure 4 Here is a flowchart of parameter comparison for one embodiment, such as Figure 4 As shown, step S104, which determines whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold, includes steps S500 to S503:

[0083] S500, if the mean value of a region of the image is less than a preset mean threshold, perform the first counting;

[0084] S501, if the regional variance of a region image is less than a preset variance threshold, perform a second counting;

[0085] S502, when the sum of the first count and the second count is less than the preset state count, the region image is determined to be unqualified;

[0086] S503, when the number of unqualified area images exceeds a preset number, the appearance image is determined to be unqualified.

[0087] To better explain steps S500 to S503, the following is an example to illustrate the implementation.

[0088] Calculate the region mean σ of the region image k As shown in the following formula:

[0089]

[0090] Calculate the regional variance μ of the region image k As shown in the following formula:

[0091]

[0092] Where k represents the k-th region of grayscale image G2, k = 1, 2, 3, 4, 5. m and n represent the length and width of the rectangular region image, with a size of w, both set to 72.

[0093] Perform the first count as follows:

[0094]

[0095] in, T1 represents the first count, and T1 represents the preset mean threshold, which includes 22-42, preferably set to 32.

[0096] Perform the second count as follows:

[0097]

[0098] in, T2 represents the second count, and T2 represents the preset variance threshold, which includes 28-48, preferably set to 38.

[0099] When the sum of the first count and the second count is less than the preset state count, the region image is determined to be unqualified, as follows:

[0100]

[0101] Among them, G2 k A value of 1 indicates that the region image is unqualified, G2 k A value of 0 indicates that the region image is acceptable. T3 represents the preset state count, with a maximum setting of 2.

[0102] If the number of non-compliant area images exceeds a preset number, the appearance image is determined to be non-compliant, as shown in the following formula:

[0103]

[0104] Where f(I) represents the mark of whether the appearance image is qualified or not. When f(I) is 1, it means that the appearance image is unqualified.

[0105] Here, T′ represents a preset quantity, the size of which is positively correlated with the number of region images and is adjusted according to the detection granularity. In one embodiment, T′ is 2-6, preferably set to 3.

[0106] The image quality inspection method based on recycling detection in any of the above embodiments, after acquiring the appearance image of the device to be recycled, performs color space conversion processing on the appearance image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, based on a comparison of each image quality parameter with a preset parameter threshold, the applicability of the appearance image is determined; wherein, the qualified appearance images are used for recycling detection. Based on this, by pre-comparing the image quality parameters, unqualified appearance images are eliminated, and qualified appearance images are retained for recycling detection, thereby improving the efficiency and accuracy of recycling detection.

[0107] Figure 5 This is a structural diagram of an image quality inspection device module based on recycling detection, as described in one embodiment. Figure 4 As shown, one embodiment of an image quality inspection apparatus based on recycling detection includes:

[0108] Image acquisition module 100 is used to acquire an external image of the device to be recycled;

[0109] Image conversion module 101 is used to perform color space conversion processing on the appearance image to generate a corresponding grayscale image;

[0110] Image segmentation module 102 is used to divide the grayscale image into regions to obtain region images;

[0111] Parameter calculation module 103 is used to calculate the image quality parameters of the region image;

[0112] The image detection module 104 is used to determine whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold; wherein, the qualified appearance image is used for recycling detection.

[0113] The aforementioned image quality inspection device based on recycling detection, after acquiring the appearance image of the equipment to be recycled, performs color space conversion processing on the appearance image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters of the region images are calculated. Finally, based on a comparison of each image quality parameter with preset parameter thresholds, the device determines whether the appearance image is qualified; qualified appearance images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified appearance images are discarded, and qualified appearance images are retained for recycling detection, improving the efficiency and accuracy of recycling detection.

[0114] This invention also provides a computer storage medium storing computer instructions that, when executed by a processor, implement the image quality inspection method based on recycling detection as described above.

[0115] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0116] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, RAM, ROM, magnetic disks, or optical disks.

[0117] Corresponding to the computer storage medium described above, one embodiment also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the image quality inspection methods based on recycling detection as described in the above embodiments.

[0118] This computer device can be a terminal, and its internal structure diagram can be as follows: Figure 6 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an image quality inspection method based on recycling detection. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0119] The aforementioned computer equipment, after acquiring an image of the device to be recycled, performs color space conversion on the image to generate a corresponding grayscale image. Further, the grayscale image is divided into regions to obtain region images, and image quality parameters for each region image are calculated. Finally, the applicability of the image is determined by comparing each image quality parameter with a preset threshold; qualified images are used for recycling detection. Based on this, by pre-comparing image quality parameters, unqualified images are removed, and qualified images are retained for recycling detection, improving the efficiency and accuracy of recycling detection.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. An image quality inspection method based on recycling detection, characterized in that, Including the following steps: Obtain an external image of the equipment to be recycled; The appearance image is subjected to color space conversion processing to generate a corresponding grayscale image; The grayscale image is divided into regions to obtain region images; Calculate the image quality parameters of the region image; The appearance image is determined to be qualified by comparing each of the image quality parameters with a preset parameter threshold; wherein, the qualified appearance image is used for recycling detection. Before the process of dividing the grayscale image into regions to obtain region images, the following steps are also included: Apply Gaussian blur to the grayscale image; The process of applying Gaussian blur to the grayscale image is as follows: in, This represents the grayscale image before Gaussian blurring. This represents a grayscale image after Gaussian blurring. , This represents the horizontal coordinate value of the origin at the top left corner of the grayscale image. This represents the coordinate value in the vertical direction relative to the origin at the top left corner of the grayscale image. Indicates the height of the grayscale image. Indicates the width of the grayscale image. This indicates the length of the rectangular window, set to 3. This represents the amplitude of the corresponding rectangular window, set to 16; the rectangular window represents the template corresponding to the Gaussian filter, as shown in the following formula: The process of dividing the grayscale image into regions to obtain region images includes the following steps: Divide the grayscale image into two or more rectangular regions to obtain the region image; The process of determining whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold includes the following steps: Based on the comparison of each of the image quality parameters with the preset parameter threshold, it is determined whether the image of the region is unqualified; The appearance image is deemed acceptable based on the number of non-compliant areas. The image quality parameters include the region mean and the region variance; the preset parameter thresholds include a preset mean threshold and a preset variance threshold; The process of determining whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold includes the following steps: If the mean value of a region in the image is less than a preset mean threshold, perform the first counting. If the regional variance of a region image is less than a preset variance threshold, perform a second counting; When the sum of the first count and the second count is less than the preset state count, the region image is determined to be unqualified; If the number of unqualified area images exceeds a preset number, the appearance image is determined to be unqualified.

2. The image quality inspection method based on recycling detection according to claim 1, characterized in that, The process of performing color space conversion on the appearance image to generate a corresponding grayscale image is as follows: in, This refers to the grayscale image. , and These represent the appearance images. The color components of the three channels: R, G, and B.

3. An image quality inspection apparatus based on recycling detection, utilizing the image quality inspection method based on recycling detection as described in any one of claims 1-2, characterized in that, include: Image acquisition module, used to acquire external images of the equipment to be recycled; The image conversion module is used to perform color space conversion processing on the appearance image to generate a corresponding grayscale image; An image segmentation module is used to divide the grayscale image into regions to obtain region images; The parameter calculation module is used to calculate the image quality parameters of the region image; The image detection module is used to determine whether the appearance image is qualified by comparing each of the image quality parameters with a preset parameter threshold; wherein, the qualified appearance image is used for recycling detection.

4. A computer storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, they implement the image quality inspection method based on recycling detection as described in any one of claims 1 to 2.

5. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the image quality inspection method based on recycling detection as described in any one of claims 1 to 2.

Images