Image processing method and system for multi-surface high-speed detection of mobile phone rear cover

Abstract

The invention relates to the technical field of image processing, and discloses an image processing method and system for multi-surface high-speed detection of a mobile phone rear cover, a feeding assembly in an execution system receives and conveys the mobile phone rear cover, and a detection assembly receives and detects the mobile phone rear cover conveyed by the feeding assembly. After detection is completed, the detected mobile phone rear covers are conveyed to the discharging assembly, the detection comprehensiveness is improved, the discharging assembly classifies the detected mobile phone rear covers, and dependence on manual operation is greatly reduced; a visual detection module in the processing system identifies whether an abnormal area exists in the mobile phone rear cover image, determines the abnormal type of the abnormal area, generates the abnormal degree of the mobile phone rear cover image, comprehensively judges the qualified state of the mobile phone rear cover according to the generation result of the abnormal degree, and generates an unqualified product label. Automatic separation of qualified products and unqualified products is achieved, convenience and accuracy of production management are improved, and the rejection rate caused by human errors is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image processing method and system for high-speed detection of multiple surfaces of a mobile phone back cover. Background Art

[0002] With the development of deep learning and machine vision technology, the use of deep learning and machine vision for defect detection of mobile phone back covers can effectively and accurately identify various types of defects, and to a certain extent realize automated and intelligent detection, which can reduce labor costs, while improving the output and quality of mobile phone back covers, and provide valuable information for monitoring and quality control of the production process. At the same time, through the combination of cameras and customized light sources, the characteristics of the inspected objects can be clearly and accurately displayed, thereby improving image quality and detection accuracy. However, most of them have not solved the problem of how to visually inspect the products comprehensively by ejecting them from the material box and conveying them by adsorption, and at the same time classifying the inspection results to distinguish the product placement.

[0003] For example, the Chinese patent application with the publication number CN118037628A discloses an IC pin defect detection method based on image processing, which includes: step S1, obtaining IC pin color image; step S2, automatic positioning and segmentation of pin area; step S3, mean filtering and denoising; step S4, based on the local dynamic extreme difference threshold algorithm 2, binary processing is performed on each filtered pin area image; step S5, establishing a low tin feature selection model and a pin curling feature selection model; step S6, automatic positioning and segmentation of non-pin area; step S7, mean filtering and denoising; step S8, based on the local dynamic extreme difference threshold algorithm 2, binary processing is performed on each filtered pin area image; step S9, establishing a tin-connection feature selection model; step S10, IC pin defect determination. It can avoid the drawbacks of traditional algorithm detection and improve the accuracy of IC pin tin-connection, low tin, and pin curling detection.

[0004] For example, a Chinese patent with the authorization announcement number CN112819812B discloses a powder bed defect detection method based on image processing, including: 1) using a camera to collect the powder image of the current layer of the powder bed in real time; 2) performing preprocessing operations to obtain a preprocessed image; 3) obtaining the variance weighted information entropy of the preprocessed image; 4) performing a binarization threshold segmentation on the variance weighted information entropy image to obtain a binarized image; 5) performing a morphological opening operation on the binarized image; 6) using a region growing method to perform a block processing on the operation result of step 5); 7) performing image post-processing and defect block labeling according to the information of each target block after the block is clustered. A powder bed defect detection method based on image processing is provided, which can quickly and accurately detect the powder image, has a wide range of scenarios, and can effectively protect the quality of part forming.

[0005] The above patents have the problems raised by the background technology: the above IC pin defect detection method obtains the color image of the IC pin, automatically locates and segments the pin area, and performs binary processing on each filtered pin area image based on the local dynamic extreme difference threshold algorithm 2, establishes a tin-poor feature selection model and a curled pin feature selection model, and automatically locates and segments the non-pin area at the same time, and performs binary processing on each filtered pin area image based on the local dynamic extreme difference threshold algorithm 2, establishes a tin-contact feature selection model, and finally obtains the IC pin defect judgment; the above powder bed defect detection method collects the powder laying image of the current layer of the powder bed in real time through a camera, performs a preprocessing operation on it to obtain a preprocessed image, obtains the variance weighted information entropy of the preprocessed image, performs binary threshold segmentation on the variance weighted information entropy image to obtain a binary image, performs morphological opening operation on the binary image, and uses region growing to cluster the result of the morphological opening operation, and performs image post-processing and defect block marking according to the information of each target block after clustering. The above two patents do not solve the problem of how to visually inspect the product comprehensively by ejecting the product from the material box and conveying it by suction, and classify the inspection results to distinguish the product placement. To solve this problem, the present invention proposes an image processing method and system for high-speed multi-faceted inspection of the back cover of a mobile phone. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the problems existing in the above-mentioned existing image processing method and system for high-speed multi-surface detection of mobile phone back cover, the present invention is proposed.

[0008] Therefore, the object of the present invention is to provide an image processing method and system for high-speed detection of multiple surfaces of a mobile phone back cover.

[0009] In order to solve the above technical problems, the present invention provides an image processing system for high-speed detection of multiple surfaces of a mobile phone back cover, comprising: an execution system and a processing system; The execution system includes a detection assembly, which is used to receive the back cover of the mobile phone and perform detection; The detection assembly includes a transmission electric cylinder, a front detection module, a conversion module and a side detection module. The transmission electric cylinder is used to place and transmit the back cover of the mobile phone to be detected. The front detection module is fixedly arranged on one side of the conversion module, and under the action of the transmission electric cylinder, the back cover of the mobile phone to be detected is transmitted for front detection of the mobile phone back cover. After the front detection, the back cover of the mobile phone is converted to the side detection module through the conversion module. The side detection module is fixedly arranged on the other side of the conversion module, and under the action of the transmission electric cylinder, the back cover of the mobile phone after the front detection is transmitted for side detection of the mobile phone back cover. The processing system includes a visual inspection module; The visual inspection module is used to identify whether there is an abnormal area in the image of the back cover of the mobile phone, determine the abnormal type of the abnormal area, and generate the abnormality degree of the image of the back cover of the mobile phone. According to the generated result of the abnormality degree, the qualified state of the back cover of the mobile phone is comprehensively judged, and a non-conforming product label is generated.

[0010] As a preferred solution of the image processing system for multi-faceted high-speed inspection of a mobile phone back cover of the present invention, wherein: the front inspection module includes a bright field camera, a front grating, a dark field camera and a bevel grating, the bright field camera is fixedly arranged above the transmission electric cylinder, the front grating is fixedly arranged in the shooting direction of the bright field camera, the front grating is used to cooperate with the bright field camera to detect defects on the front of the mobile phone back cover, the dark field camera is fixedly arranged above the transmission electric cylinder and fixedly arranged on one side of the bright field camera, the bevel grating is fixedly arranged in the shooting direction of the dark field camera, and the bevel grating is used to cooperate with the dark field camera to detect defects on the front of the mobile phone back cover; The conveying electric cylinder comprises a front inspection positioning jig, a conveying sliding seat and a side inspection positioning jig. The conveying sliding seat is driven by the conveying electric cylinder to move close to or away from the conversion module. The front inspection positioning jig and the side inspection positioning jig are used to place the back cover of the mobile phone to be inspected. The conveying sliding seat is slidingly connected to the front inspection positioning jig and the side inspection positioning jig respectively. When the back cover of the mobile phone is sucked out of the loading box, the moving electric cylinder drives the material picking bracket to move to the detection assembly, and the material picking bracket is driven by the material picking electric cylinder to move and place it on the front inspection positioning jig. The conveying electric cylinder drives the conveying sliding seat to move along the length direction of the conveying sliding belt. The front inspection positioning jig moves to the conversion module driven by the conveying sliding seat. The back cover of the mobile phone on the front inspection positioning jig is successively inspected by the bright field camera and the front grating as well as the dark field camera and the inclined grating to comprehensively generate a front image of the back cover of the mobile phone.

[0011] As a preferred solution of the image processing system for multi-sided high-speed inspection of the back cover of a mobile phone described in the present invention, wherein: the conversion module includes a transfer pick-up and release cylinder and a conversion electric cylinder, the conversion electric cylinder is connected to the transfer pick-up and release cylinder, the conversion electric cylinder is used to control the transfer pick-up and release cylinder to move toward or away from the transmission electric cylinder, the side inspection module includes a side grating and a side scanning camera, the side scanning cameras are respectively fixed on both sides of the transmission electric cylinder, the side gratings are respectively fixed on both sides of the transmission electric cylinder and fixed above the side scanning camera, the side gratings are used to cooperate with the side scanning camera to detect defects on the side of the back cover of the mobile phone, the back cover of the mobile phone on the side inspection positioning jig is inspected by the side scanning camera and the side grating to generate a side image of the back cover of the mobile phone.

[0012] As a preferred solution of the image processing system for multi-sided high-speed detection of the back cover of a mobile phone described in the present invention, the front of the back cover of the mobile phone is detected by a combination of a front grating and a bright field camera and a combination of a bevel grating and a dark field camera, and the side of the back cover of the mobile phone is detected by a combination of a side grating and a side scanning camera, and the front image and the side image of the back cover of the mobile phone are captured respectively, and the back cover image of the mobile phone is generated, and it is identified whether there is an abnormal area in the image of the back cover of the mobile phone, and the abnormal type of the abnormal area is determined, and the abnormal type includes scratches, deformation and stains, and the abnormal degree of the back cover image of the mobile phone with abnormal areas is generated, and the abnormal degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness. According to the generated result of the abnormal degree, the qualified state of the back cover of the mobile phone is comprehensively judged, and the judgment result of the back cover of the mobile phone is generated.

[0013] As a preferred solution of the image processing system for high-speed multi-surface detection of a mobile phone back cover of the present invention, the logic of identifying whether an abnormal area appears in the image of the mobile phone back cover includes: Calculate the grayscale co-occurrence matrix of the mobile phone back cover image, analyze the contrast, homogeneity and correlation of the grayscale co-occurrence matrix, configure the contrast threshold, homogeneity threshold and correlation threshold, and compare the contrast threshold, homogeneity threshold and correlation threshold with the contrast, homogeneity and correlation of the grayscale co-occurrence matrix of the mobile phone back cover image to determine whether there is an abnormal area in the mobile phone back cover image.

[0014] As a preferred solution of the image processing system for multi-faceted high-speed detection of a mobile phone back cover of the present invention, the function expression of the gray level co-occurrence matrix of the mobile phone back cover image is as follows: ; In the formula, Represents grayscale value and The frequency of pixel pairs co-appearing in the image of the mobile phone back cover, Indicates that the image of the phone's back cover is at position The gray value at and Indicates the relative position between adjacent pixels.

[0015] As a preferred solution of the image processing system for multi-faceted high-speed detection of a mobile phone back cover of the present invention, the function expression of whether the image of the mobile phone back cover has an abnormal area is as follows: ; In the formula, Indicates whether the image of the back cover of the mobile phone has an abnormal area. 1 indicates that the image of the back cover of the mobile phone has an abnormal area, and 0 indicates that the image of the back cover of the mobile phone has no abnormal area. Represents the contrast of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the contrast threshold, Represents the homogeneity of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the homogeneity threshold, Represents the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the correlation threshold, Indicates situations other than the above.

[0016] As a preferred solution of the image processing system for high-speed multi-surface inspection of a mobile phone back cover of the present invention, the logic for determining the abnormal type of the abnormal area includes: If the image of the back cover of the mobile phone is of extreme contrast value and base homogeneity value, the abnormal type of the abnormal area is determined to be stain; If the image of the back cover of the mobile phone is an extreme value of contrast and correlation, it is determined that the abnormal type of the abnormal area is a scratch; If the image of the back cover of the mobile phone is an extreme value of contrast, a base value of homogeneity, and an extreme value of correlation, then the abnormal type of the abnormal area is determined to be deformation.

[0017] As a preferred solution of the image processing system for multi-faceted high-speed detection of a mobile phone back cover of the present invention, wherein: the abnormality degree of the mobile phone back cover image with abnormal area generated, the abnormality degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness, and the qualified state of the mobile phone back cover is comprehensively judged according to the generated result of the abnormality degree. The function expression for comprehensively judging the qualified state of the mobile phone back cover is as follows: ; In the formula, Indicates the qualification of the back cover of the mobile phone. represents the scratch length, Indicates the scratch depth, represents the scratch depth threshold, Represents the total stain area of ​​the mobile phone back cover image, Indicates the maximum stain area, represents the average stain contrast of the mobile phone back cover image, represents the stain contrast threshold, Indicates the edge smoothness of the mobile phone back cover image. represents the edge smoothing threshold; Configure the qualification threshold, and generate the judgment result of the mobile phone back cover according to the comparison between the qualification of the mobile phone back cover and the qualification threshold. The rules for generating the judgment result include: If the qualification degree of the mobile phone back cover is less than or equal to the qualification threshold, it is displayed that the mobile phone back cover is qualified; If the qualification degree of the mobile phone back cover is greater than the qualification threshold, the mobile phone back cover is displayed as unqualified and a label of unqualified product is generated.

[0018] An image processing method for high-speed multi-surface detection of a mobile phone back cover comprises: S1, receiving and conveying the mobile phone back cover; S2, receiving the mobile phone back cover conveyed by the feeding assembly and performing inspection; S3, identifying whether there is an abnormal area in the mobile phone back cover image generated during the detection process; S4, determining the abnormal type of the abnormal area, and generating the abnormal degree of the mobile phone back cover image; S5. Comprehensively judging the qualified state of the mobile phone back cover according to the generated result of the abnormality degree; S6. Classify according to the qualified status of the mobile phone back cover.

[0019] A computer device comprises a memory for storing instructions and a processor for executing the instructions, so that the computer device executes an image processing method for high-speed detection of multiple surfaces of a mobile phone back cover.

[0020] A computer-readable storage medium stores a computer program, which, when executed, implements an image processing method for high-speed multi-surface detection of a mobile phone back cover.

[0021] Beneficial effects of the present invention: The present invention receives and conveys the mobile phone back cover through the loading assembly in the execution system, provides continuous product supply for subsequent processes, significantly reduces loading time, ensures the continuity of the entire detection process, and avoids delays caused by module conversion. The detection assembly receives and detects the mobile phone back cover conveyed by the loading assembly, and conveys the detected mobile phone back cover to the unloading assembly when the detection is completed. Various defects of the mobile phone back cover are identified under different lighting conditions, increasing the flexibility and accuracy of detection, ensuring that all possible defects of the mobile phone back cover are examined, and improving the comprehensiveness of detection. The unloading assembly is very important for detection. The mobile phone back covers are classified, and based on the detection results, the products are automatically classified into different material boxes, which greatly reduces the dependence on manual operation; the visual inspection module in the processing system identifies whether there are abnormal areas in the mobile phone back cover image, determines the abnormal type of the abnormal area, and generates the abnormality degree of the mobile phone back cover image. According to the generated results of the abnormality degree, the qualified state of the mobile phone back cover is comprehensively judged, and a non-conforming product label is generated to realize the automatic separation of qualified and non-conforming products, thereby improving the convenience and accuracy of production management, reducing the scrap rate caused by human errors, improving the utilization rate of raw materials, and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 This is a system structure diagram of an image processing system for high-speed multi-surface detection of a mobile phone back cover according to the present invention; Figure 2 A method flow chart of an image processing method for high-speed detection of multiple surfaces of a mobile phone back cover according to the present invention; Figure 3 This is a general structural diagram of an execution system of an image processing system for high-speed multi-surface inspection of a mobile phone back cover according to the present invention; Figure 4 This is a structural diagram of a feeding assembly of an image processing system for high-speed multi-surface inspection of a mobile phone back cover according to the present invention; Figure 5 This is a structural diagram of a detection assembly of an image processing system for high-speed multi-surface detection of a mobile phone back cover according to the present invention; Figure 6 This is an enlarged view of the front grating and the inclined grating of an image processing system for high-speed multi-surface detection of a mobile phone back cover according to the present invention; Figure 7 This is an enlarged view of the side grating and side scanning camera of an image processing system for high-speed multi-surface inspection of a mobile phone back cover according to the present invention; Figure 8 The present invention is a structural diagram of a blanking assembly of an image processing system for high-speed multi-surface inspection of a mobile phone back cover.

[0023] Figure numerals: 1, feeding assembly; 2, detection assembly; 3, unloading assembly; 4, machine body; 11, feeding module; 12, feeding screw; 13, material picking truss; 111, feeding box; 112, box seat; 113, feeding electric cylinder; 121, bracket seat; 122, moving electric cylinder; 131, feeding sliding seat; 132, picking electric cylinder; 133, picking bracket; 134, adsorption cylinder; 21, transmission electric cylinder; 22, front inspection module; 23, conversion module; 24, side inspection module; 211, front inspection positioning jig; 212, transmission sliding seat; 2 13. Side inspection positioning jig; 221. Bright field camera; 222. Front grating; 223. Dark field camera; 224. Bevel grating; 231. Transfer pick-up and release cylinder; 232. Conversion electric cylinder; 241. Side grating; 242. Side scanning camera; 31. Unloading module; 32. Unloading screw; 33. Unloading truss; 311. Unloading box; 312. Storage box; 313. Unloading electric cylinder; 321. Support frame; 322. Conveying electric cylinder; 331. Unloading sliding seat; 332. Unloading electric cylinder; 333. Unloading bracket; 334. Unloading cylinder. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0026] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0027] Example 1

[0028] In this embodiment, a system structure diagram of an image processing system for high-speed detection of multiple surfaces of a mobile phone back cover is provided. Figure 1 As shown, an image processing system for high-speed inspection of multiple surfaces of a mobile phone back cover includes an execution system and a processing system.

[0029] like Figure 3As shown, the execution system includes a loading assembly 1, a detection assembly 2 and a unloading assembly 3. The loading assembly 1 is used to receive and convey the mobile phone back cover from the output end of the injection molding machine. The detection assembly 2 is used to receive and inspect the mobile phone back cover conveyed by the loading assembly 1. When the inspection is completed, the inspected mobile phone back cover is conveyed to the unloading assembly 3. The unloading assembly 3 is used to classify the inspected mobile phone back covers and convey them to the packaging process.

[0030] like Figure 4 As shown, the feeding assembly 1 includes a feeding module 11, a feeding screw 12 and a picking truss 13. The feeding module 11 is used to receive the back cover of the mobile phone to be inspected. The picking truss 13 is connected to the feeding screw 12 and moves to the feeding module 11 or away from the feeding module 11 under the action of the feeding screw 12. The picking truss 13 is also used to take out the back cover of the mobile phone to be inspected from the feeding module 11 when moving to the feeding module 11, and transport the back cover of the mobile phone to the inspection assembly 2 when moving away from the feeding module 11.

[0031] The feeding module 11 includes a feeding box 111, a box seat 112 and a feeding electric cylinder 113. The feeding box 111 is used to store the back cover of the mobile phone to be tested. The box seat 112 is located in the feeding box 111 and is used to support the back cover of the mobile phone. The feeding electric cylinder 113 is connected to the side of the box seat 112 away from the back cover of the mobile phone, and is used to control the movement of the box seat 112 along the feeding box 111 to complete the feeding control when taking the material from the back cover of the mobile phone.

[0032] The feeding screw 12 includes a support seat 121 and a movable electric cylinder 122. The support seat 121 is fixed on the machine body 4 (such as Figure 3As shown in the figure, the mobile electric cylinder 122 is fixed on the bracket seat 121, the material picking truss 13 includes a feeding sliding seat 131, a feeding electric cylinder 132, a feeding bracket 133 and an adsorption cylinder 134, the feeding sliding seat 131 is slidably connected to the mobile electric cylinder 122, the feeding sliding seat 131 is also connected to the feeding electric cylinder 132, the output direction of the feeding electric cylinder 132 is perpendicular to the output direction of the mobile electric cylinder 122, the feeding bracket 133 is slidably connected to the feeding electric cylinder 132, the adsorption cylinder 134 is arranged on the feeding bracket 133, the mobile electric cylinder 122 is used to drive the feeding sliding seat 131 to move toward or away from the feeding box 111, so as to drive the feeding bracket 133 to move to the feeding box 111 or moves to the detection assembly 2, the material picking electric cylinder 132 is used to control the material picking bracket 133 to extend into the loading box 111 or move away from the loading box 111, and the adsorption cylinder 134 is used to adsorb the back cover of the mobile phone, so that when the back cover of the mobile phone needs to be taken out from the loading box 111, the moving electric cylinder 122 drives the loading sliding seat 131 to move and synchronously drives the material picking bracket 133 to move to the loading box 111. At this time, the material picking electric cylinder 132 controls the material picking bracket 133 to move and extend into the loading box 111, so that the adsorption cylinder 134 adsorbs the back cover of the mobile phone. After the back cover of the mobile phone is adsorbed, the material picking electric cylinder 132 drives the material picking bracket 133 to reset and take the back cover of the mobile phone out of the loading box 111. At this time, the feeding module 11 drives the box seat 112 to feed the thickness of a mobile phone back cover, forming a feeding and replenishing material for the mobile phone back cover during the feeding. After the mobile phone back cover is sucked out of the feeding box 111, the moving electric cylinder 122 drives the material picking bracket 133 to move to the detection assembly 2, completes the material picking of the mobile phone back cover and transports it to the detection assembly 2.

[0033] like Figure 5 As shown, the detection assembly 2 includes a conveying electric cylinder 21, a front detection module 22, a conversion module 23 and a side detection module 24. The conveying electric cylinder 21 is used to place and convey the back cover of the mobile phone to be detected. The front detection module 22 is fixedly arranged on one side of the conversion module 23, and under the action of the conveying electric cylinder 21, the back cover of the mobile phone to be detected is conveyed for front detection of the back cover of the mobile phone. After the front detection, the back cover of the mobile phone is converted to the side detection module 24 through the conversion module 23. The side inspection module 24 is fixedly arranged on the other side of the conversion module 23, and under the action of the conveying electric cylinder 21, the back cover of the mobile phone after the front detection is conveyed for side detection of the back cover of the mobile phone, and the back cover of the mobile phone is transported to the unloading assembly 3 when it is away from the side detection module 24, wherein A represents an enlarged view of the front grating 222 and the bevel grating 224, and B represents an enlarged view of the side grating 241 and the side scanning camera 242.

[0034] The front inspection module 22 includes a bright field camera 221, a front grating 222, a dark field camera 223 and a bevel grating 224. The bright field camera 221 is fixedly arranged above the transmission cylinder 21, the front grating 222 is fixedly arranged in the shooting direction of the bright field camera 221, and the front grating 222 is used to cooperate with the bright field camera 221 to detect defects on the front of the back cover of the mobile phone. The dark field camera 223 is fixedly arranged above the transmission cylinder 21 and fixedly arranged on one side of the bright field camera 221, and the bevel grating 224 is fixedly arranged in the shooting direction of the dark field camera 223. The bevel grating 224 is used to cooperate with the dark field camera 223 to detect defects on the front of the back cover of the mobile phone. The enlarged images of the front grating 222 and the bevel grating 224 are shown in FIG. Figure 6 shown.

[0035] The transmission electric cylinder 21 includes a front inspection positioning jig 211, a transmission sliding seat 212 and a side inspection positioning jig 213. The transmission sliding seat 212 is driven by the transmission electric cylinder 21 to move close to or away from the conversion module 23. The front inspection positioning jig 211 and the side inspection positioning jig 213 are used to place the back cover of the mobile phone to be inspected. The transmission sliding seat 212 is slidably connected with the front inspection positioning jig 211 and the side inspection positioning jig 213 respectively. When the back cover of the mobile phone is sucked out of the loading box 111, the moving electric cylinder 122 drives the material picking bracket 133 to move to the detection assembly 2, and the material picking bracket 133 is driven by the material picking electric cylinder 132 to move and place it on the front inspection positioning jig 211. At this time, the mobile phone back cover is sucked out of the loading box 111. The material electric cylinder 132 drives the material picking bracket 133 to move and reset, and is moved to the loading box 111 driven by the moving electric cylinder 122 to pick up the next round of mobile phone back cover. When the mobile phone back cover is placed on the positive inspection and positioning jig 211, the conveying electric cylinder 21 drives the conveying sliding seat 212 to move along the length direction of the conveying sliding belt. At the same time, the positive inspection and positioning jig 211 is driven by the conveying sliding seat 212 to move to the conversion module 23. At this time, the mobile phone back cover on the positive inspection and positioning jig 211 is sequentially inspected by the bright field camera 221 and the front grating 222, as well as the dark field camera 223 and the bevel grating 224, to comprehensively generate a front image of the mobile phone back cover.

[0036] The conversion module 23 includes a transfer pick-up and release cylinder 231 and a conversion electric cylinder 232. The conversion electric cylinder 232 is connected to the transfer pick-up and release cylinder 231. The conversion electric cylinder 232 is used to control the transfer pick-up and release cylinder 231 to move toward or away from the transmission electric cylinder 21. When the positive inspection and positioning jig 211 moves to the conversion module 23 under the drive of the transmission sliding seat 212, the transfer pick-up and release cylinder 231 moves toward the transmission electric cylinder 21 under the drive of the conversion electric cylinder 232, and adsorbs the back cover of the mobile phone on the positive inspection and positioning jig 211. After the back cover of the mobile phone is adsorbed, the transfer pick-up and release cylinder 231 moves away from the transmission electric cylinder 21 under the control of the conversion electric cylinder 232. At this time, the transmission electric cylinder 21 drives the transmission sliding seat 212 to move along the length direction of the transmission sliding belt, so that the positive inspection and positioning jig 21 1 is driven by the conveying sliding seat 212 to move away from the conversion module 23 and move to the front inspection module 22 to carry out the next round of inspection of the mobile phone back cover by the front inspection module 22. At the same time, the side inspection positioning jig 213 is driven by the conveying sliding seat 212 to move to the conversion module 23. The transfer pick-up and release cylinder 231 is driven by the conversion cylinder 232 to move toward the conveying cylinder 21 and place the adsorbed mobile phone back cover on the side inspection positioning jig 213. When the next round of mobile phone back cover passes the inspection of the front inspection module 22, the front inspection positioning jig 211 is driven by the conveying sliding seat 212 to move to the conversion module 23. At this time, the side inspection positioning jig 213 is driven by the conveying sliding seat 212 to move to the side inspection module 24 to complete the inspection of the side of the mobile phone back cover.

[0037] The side inspection module 24 includes a side grating 241 and a side scanning camera 242. The side scanning cameras 242 are fixedly mounted on both sides of the conveying cylinder 21. The side gratings 241 are fixedly mounted on both sides of the conveying cylinder 21 and fixedly mounted above the side scanning cameras 242 (the enlarged view of the side grating 241 and the side scanning camera 242 is shown in FIG. Figure 7As shown in the figure, the side grating 241 is used to cooperate with the side scanning camera 242 to detect defects on the side of the back cover of the mobile phone. When the side inspection positioning jig 213 is driven by the conveying sliding seat 212 to move to the side inspection module 24, the back cover of the mobile phone on the side inspection positioning jig 213 is inspected by the side scanning camera 242 and the side grating 241 to generate a side image of the back cover of the mobile phone. After being inspected by the side scanning camera 242 and the side grating 241, the conveying electric cylinder 21 drives the conveying sliding seat 212 to move along the length direction of the conveying sliding belt, so that the side inspection positioning jig 213 is driven by the conveying sliding seat 212 to move down. Move to the unloading assembly 3. When the unloading assembly 3 takes out the back cover of the mobile phone on the side inspection positioning jig 213, the back cover of the mobile phone that has been inspected by the front inspection module 22 for the next round has been moved to the conversion module 23. At this time, the conveying sliding belt moves along the length direction of the conveying sliding belt under the drive of the conveying electric cylinder 21, so that the side inspection positioning jig 213 is driven by the conveying sliding belt to approach the conversion module 23 to receive the back cover of the mobile phone that has been inspected by the front inspection module 22 for the next round, and convert the back cover of the mobile phone to the side inspection positioning jig 213 through the conversion module 23, so as to carry out the next round of inspection of the back cover of the mobile phone by the side inspection module 24.

[0038] like Figure 8 As shown, the unloading assembly 3 includes a unloading module 31, a unloading screw 32 and a discharge truss 33. The unloading module 31 is used to store the back cover of the mobile phone after inspection. The discharge truss 33 is connected to the unloading screw 32, and moves to the inspection assembly 2 or away from the inspection assembly 2 under the action of the unloading screw 32. The discharge truss 33 is also used to take out the back cover of the mobile phone after inspection from the inspection assembly 2 when moving to the inspection assembly 2, and transport the back cover of the mobile phone to the unloading module 31 when moving away from the inspection assembly 2.

[0039] The unloading module 31 includes a unloading box 311, a storage box 312 and an unloading electric cylinder 313. The unloading box 311 is used to store the back cover of the mobile phone after inspection. The storage box 312 is located in the unloading box 311 and is used to support the back cover of the mobile phone. The unloading electric cylinder 313 is connected to the side of the unloading box 311 away from the back cover of the mobile phone, and is used to control the storage box 312 to move along the unloading box 311 to complete the feeding control when unloading the back cover of the mobile phone.

[0040] The unloading screw 32 includes a support frame 321 and a conveying cylinder 322. The support frame 321 is fixed on the body 4, and the conveying cylinder 322 is fixed on the support frame 321. The unloading truss includes a unloading sliding seat 331, a discharge cylinder 332, a discharge bracket 333 and a discharge cylinder 334. The unloading sliding seat 331 is slidably connected to the conveying cylinder 322. The unloading sliding seat 331 is also connected to the discharge cylinder 332. The output direction of the discharge cylinder 332 is perpendicular to the output direction of the conveying cylinder 322. The discharge bracket 333 is slidably connected to the discharge cylinder 332. The discharge cylinder 334 is arranged on the discharge bracket 333. The conveying cylinder 322 is used to drive the unloading sliding seat 331 to move toward or away from the unloading box 311, so as to drive the discharge bracket 333 to move to the detection assembly 2 or moves to the unloading box 311, the unloading electric cylinder 332 is used to control the unloading bracket 333 to extend into the unloading box 311 or move away from the unloading box 311, and the unloading cylinder 334 is used to adsorb the back cover of the mobile phone, so that when the back cover of the mobile phone needs to be taken out from the detection assembly 2, the conveying electric cylinder 322 drives the unloading sliding seat 331 to move and synchronously drives the unloading bracket 333 to move to the detection assembly 2. At this time, the unloading electric cylinder 332 controls the unloading bracket 333 to move and extend into the detection assembly 2, so that the unloading cylinder 334 adsorbs the back cover of the mobile phone. After the back cover of the mobile phone is adsorbed, the unloading electric cylinder 332 drives the unloading bracket 333 to reset and take the back cover of the mobile phone out of the detection assembly 2. After the back cover of the mobile phone is adsorbed and taken out, the conveying electric cylinder 322 drives the unloading bracket 333 to move to the unloading box 311.

[0041] The unloading box 311 includes a qualified box and an unqualified box. At this time, the mobile phone back covers that are sucked out include a first mobile phone back cover and a second mobile phone back cover. The two mobile phone back covers are respectively labeled whether there are unqualified products according to the detection results of the detection assembly 2. If the first mobile phone back cover and the second mobile phone back cover are both qualified products, the two mobile phone back covers are sucked out and then the conveying electric cylinder 322 drives the unloading bracket 333 to move to the qualified box in sequence. The unloading electric cylinder 332 controls the unloading bracket 333 to move and extend into the qualified box. At this time, the unloading module 31 drives the qualified box to be unqualified. The storage box 312 absorbs the thickness of a mobile phone back cover, forming an absorption classification of the mobile phone back covers in the blanking; if the first mobile phone back cover and the second mobile phone back cover are both unqualified products, the two mobile phone back covers are sucked out and then the conveying electric cylinder 322 drives the discharge bracket 333 to move to the unqualified box in sequence. At this time, the blanking module 31 drives the storage box 312 in the unqualified box to absorb the thickness of a mobile phone back cover, forming an absorption classification of the mobile phone back covers in the blanking; if the first mobile phone back cover is a qualified product, and the second mobile phone back cover is an unqualified product ... then the two mobile phone back covers are sucked out and then the conveying electric cylinder 322 drives the discharge bracket 333 to move to the unqualified box in sequence. After the back cover of the mobile phone is sucked out, the conveying electric cylinder 322 drives the discharge bracket 333 to move the second mobile phone back cover to the unqualified box first. At this time, the unloading module 31 drives the storage box 312 in the unqualified box to absorb the thickness of a mobile phone back cover, forming an absorption classification of the second mobile phone back cover in the unloading process, and then moves the first mobile phone back cover to the qualified box. At this time, the unloading module 31 drives the storage box 312 in the qualified box to absorb the thickness of a mobile phone back cover, forming an absorption classification of the first mobile phone back cover in the unloading process; if the first mobile phone back cover is unqualified, and the second mobile phone back cover is unqualified ... If the two mobile phone back covers are qualified products, then after the two mobile phone back covers are sucked out, the conveying electric cylinder 322 drives the discharge bracket 333 to move the second mobile phone back cover to the qualified box first. At this time, the unloading module 31 drives the storage box 312 in the qualified box to absorb the thickness of a mobile phone back cover, forming an absorption classification of the second mobile phone back cover in the unloading process, and then moves the first mobile phone back cover to the unqualified box. At this time, the unloading module 31 drives the storage box 312 in the unqualified box to absorb the thickness of a mobile phone back cover, forming an absorption classification of the first mobile phone back cover in the unloading process.

[0042] The processing system includes a visual inspection module.

[0043] The visual inspection module is used to identify whether there are abnormal areas in the image of the back cover of the mobile phone, determine the abnormal type of the abnormal area, and generate the abnormality degree of the image of the back cover of the mobile phone. According to the generated results of the abnormality degree, the qualified status of the back cover of the mobile phone is comprehensively judged and a non-conforming product label is generated.

[0044] The front of the mobile phone back cover is detected by a combination of the front grating 222 and the bright field camera 221 and the combination of the bevel grating 224 and the dark field camera 223, and the side of the mobile phone back cover is detected by a combination of the side grating 241 and the side scanning camera 242, the angles and positions of the front grating 222, the bevel grating 224 and the side grating 241 are determined, and the illumination intensity of the front grating 222, the bevel grating 224 and the side grating 241 is adjusted, and the resolution and frame rate of the bright field camera 221, the dark field camera 223 and the side scanning camera 242 are determined at the same time, and the front image and the side image of the mobile phone back cover are captured respectively, and the mobile phone back cover image is generated, and it is identified whether there is an abnormal area in the mobile phone back cover image, and the abnormal type of the abnormal area is determined, and the abnormal type includes scratches, deformation and stains, and the abnormal degree of the mobile phone back cover image with the abnormal area is generated, and the abnormal degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness, and the qualified state of the mobile phone back cover is comprehensively judged according to the generated result of the abnormal degree, and the judgment result of the mobile phone back cover is generated.

[0045] When capturing the front image of the back cover of the mobile phone, the front grating 222 is located above the back cover of the mobile phone, and the light is reflected from the surface of the back cover of the mobile phone into the lens of the bright field camera 221, which can clearly show the scratches, fingerprints, stains and other obvious defects on the surface of the back cover of the mobile phone due to reflection. At the same time, it is necessary to ensure that the front grating 222 can evenly cover the shooting range of the bright field camera 221 in the front inspection module 22 to avoid missed detection or misjudgment due to uneven lighting. The position of the front grating 222 is placed in the same direction as the shooting of the bright field camera 221, located above the back cover of the mobile phone, which can enhance the detailed features of the surface of the object. Generally, the angle of the front grating 222 is 0°, which represents the angle between the illumination angle of the front grating 222 and the vertical axis of the surface of the back cover of the mobile phone. The illumination intensity of the front grating 222 needs to be adjusted to an appropriate level according to actual needs to ensure that the features in the front image are clearly visible and avoid loss of details due to overexposure. The back cover of the mobile phone is directly illuminated by the bevel grating 224, and the dark field camera 223 is set at the back of the mobile phone. The scattered light generated when light shines on the defective part is used to identify the defect. This scattered light can enter the lens of the dark field camera 223, while the normal smooth surface will not scatter light strongly, so it appears as a dark part in the image. It can detect tiny dents and edge damage on the back cover of the mobile phone, which may not be easy to be found under front lighting. The bevel grating 224 is placed at a small angle to the surface of the back cover of the mobile phone to highlight the edge and contour of the back cover of the mobile phone. The angle of the bevel grating 224 is usually about 15° to 45°. The angle of the bevel grating 224 represents the angle of the illumination angle of the bevel grating 224 relative to the horizontal axis of the surface of the back cover of the mobile phone. At the same time, it is also necessary to determine the position and angle of the bevel grating 224 by actually observing the lighting effect of the back cover of the mobile phone to ensure that the edge and contour of the back cover of the mobile phone are clearly visible. The illumination intensity of the bevel grating 224 needs to be adjusted to an appropriate level according to actual needs to ensure that the features in the front image are clearly visible while avoiding loss of details due to overexposure.

[0046] When capturing the side image of the back cover of the mobile phone, the back cover of the mobile phone is directly illuminated by the side grating 241, and the light is reflected from the side of the back cover of the mobile phone into the lens of the side scanning camera 242, which can clearly show the scratches, stains, dents and uneven edges on the side of the back cover of the mobile phone. Here, the side grating 241 is placed on both sides of the back cover of the mobile phone, and the angle of the lighting direction of the side grating 241 is 0° with the horizontal axis of the surface of the back cover of the mobile phone. The lighting intensity of the side grating 241 needs to be adjusted to an appropriate level according to actual needs to ensure that the features in the side image are clearly visible and avoid loss of details due to overexposure.

[0047] The logic for identifying whether an abnormal area appears in the image of the back cover of a mobile phone includes: Calculate the grayscale co-occurrence matrix of the mobile phone back cover image, analyze the contrast, homogeneity and correlation of the grayscale co-occurrence matrix, configure the contrast threshold, homogeneity threshold and correlation threshold, and compare the contrast threshold, homogeneity threshold and correlation threshold with the contrast, homogeneity and correlation of the grayscale co-occurrence matrix of the mobile phone back cover image to determine whether there is an abnormal area in the mobile phone back cover image.

[0048] The function expression of the gray-level co-occurrence matrix of the mobile phone back cover image is as follows: ; In the formula, Represents grayscale value and The frequency of pixel pairs co-appearing in the image of the mobile phone back cover, Indicates that the image of the phone's back cover is at position The gray value at and Indicates the relative position between adjacent pixels.

[0049] What needs to be explained is that co-occurrence refers to the gray value and The pixel pairs appear simultaneously when they are adjacent in the image of the back cover of the mobile phone; The value range is between 0 and 1, and all The sum of is 1; usually the gray value is a non-negative integer; and Usually an integer, it refers to the offset of adjacent pixels. In the standard gray-level co-occurrence matrix and The value of may be 1 and -1 (i.e., upward, downward, left, right, or diagonal offset), or it may be a larger value, indicating different spatial distances; Refers to the logical symbol used to check whether the left and right conditions are true at the same time.

[0050] The function expression of the contrast of the grayscale co-occurrence matrix of the mobile phone back cover image is as follows: ; In the formula, Represents the contrast of the gray-level co-occurrence matrix of the mobile phone back cover image, Represents grayscale value and The frequency with which pixel pairs co-occur in images of mobile phone back covers.

[0051] What needs to be explained is: the contrast of the grayscale co-occurrence matrix of the mobile phone back cover image It is the degree of difference between different grayscale values ​​in the mobile phone back cover image. If there is a clear boundary between light and dark areas or a strong texture change in the mobile phone back cover image, the contrast will be higher; on the contrary, a uniform area (close grayscale values) will result in a lower contrast.

[0052] The function expression of the homogeneity of the gray-level co-occurrence matrix of the mobile phone back cover image is as follows: ; In the formula, Represents the homogeneity of the gray-level co-occurrence matrix of the mobile phone back cover image, Represents grayscale value and The frequency with which pixel pairs co-occur in images of mobile phone back covers.

[0053] What needs to be explained is: The value range is from 0 to 255. When the grayscale difference is 0, it means the grayscale values ​​are the same. When the grayscale difference is 255, it means the grayscale values ​​are completely different. Homogeneity of the grayscale co-occurrence matrix of the mobile phone back cover image It measures the similarity between adjacent pixels in the mobile phone back cover image. When the grayscale values ​​of adjacent pixels in the mobile phone back cover image are slightly different, the homogeneity is high, which means that the texture of the mobile phone back cover image is relatively uniform. If the grayscale values ​​of adjacent pixels are significantly different, the homogeneity is low, which means that there are texture changes or uneven areas in the mobile phone back cover image, or there are edges, textures or other irregular areas in the mobile phone back cover image.

[0054] The function expression of the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image is as follows: ; In the formula, Represents the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image, Represents grayscale value and The frequency of pixel pairs co-appearing in the image of the mobile phone back cover, Represents grayscale value The mean of Represents grayscale value The mean of Represents grayscale value The standard deviation of Represents grayscale value The standard deviation of .

[0055] What needs to be explained is: grayscale value The mean and grayscale value The mean Usually within the grayscale range, the specific value depends on the grayscale distribution of the mobile phone back cover image; grayscale value Standard Deviation and grayscale value Standard Deviation Usually a positive value, it refers to the degree of dispersion of grayscale distribution. The larger the value, the more dispersed the grayscale distribution. The correlation of the grayscale co-occurrence matrix of the mobile phone back cover image It measures the linear relationship between two grayscale values, reflecting whether the grayscale changes of different pixel pairs in the mobile phone back cover image show a certain linear relationship, and the value range is between -1 and 1. Close to 1, indicating that the linear relationship between the two gray values ​​is very strong, which usually means that the gray changes in the mobile phone back cover image are consistent and the regional texture is regular. If it is close to -1, it means that the relationship between the two gray values ​​is inversely linear, which usually means that the grayscale change in the image shows a large contrast. If it is close to 0, it means that there is no obvious linear relationship between the two grayscale values, which usually means that the grayscale changes in the mobile phone back cover image are relatively random, and noise or disordered texture may appear.

[0056] The function expression for whether the image of the back cover of the mobile phone has an abnormal area is as follows: ; In the formula, Indicates whether the image of the back cover of the mobile phone has an abnormal area. 1 indicates that the image of the back cover of the mobile phone has an abnormal area, and 0 indicates that the image of the back cover of the mobile phone has no abnormal area. Represents the contrast of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the contrast threshold, Represents the homogeneity of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the homogeneity threshold, Represents the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the correlation threshold, Indicates situations other than the above.

[0057] The logic for determining the anomaly type of the anomaly area includes: If the contrast of the gray-level co-occurrence matrix of the mobile phone back cover image is greater than the contrast threshold, the mobile phone back cover image is recorded as the contrast extreme value; If the contrast of the gray level co-occurrence matrix of the mobile phone back cover image is less than or equal to the contrast threshold, the mobile phone back cover image is recorded as the contrast base value; If the homogeneity of the gray level co-occurrence matrix of the mobile phone back cover image is greater than or equal to the homogeneity threshold, the mobile phone back cover image is recorded as the homogeneity extreme value; If the homogeneity of the gray level co-occurrence matrix of the mobile phone back cover image is less than the homogeneity threshold, the mobile phone back cover image is recorded as the homogeneity base value; If the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image is greater than the correlation threshold, the mobile phone back cover image is recorded as the correlation extreme value; If the correlation of the gray level co-occurrence matrix of the mobile phone back cover image is less than or equal to the correlation threshold, the mobile phone back cover image is recorded as the correlation base value.

[0058] If the image of the back cover of the mobile phone is of extreme contrast value and base homogeneity value, the abnormal type of the abnormal area is determined to be stain; If the image of the back cover of the mobile phone is an extreme value of contrast and correlation, it is determined that the abnormal type of the abnormal area is a scratch; If the image of the back cover of the mobile phone is an extreme value of contrast, a base value of homogeneity, and an extreme value of correlation, then the abnormal type of the abnormal area is determined to be deformation.

[0059] Generate the abnormality degree of the mobile phone back cover image with abnormal area. The abnormality degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness. The function expression of scratch length is as follows: ; In the formula, represents the scratch length, represents the number of points on the scratch profile, Represents the distance between two adjacent contour points.

[0060] It should be explained that when the scratches are identified on the back cover of the mobile phone, the scratch outline is regarded as composed of many points, and the distance between two adjacent outline points is Calculated using the Euclidean distance formula.

[0061] The function expression of scratch depth is as follows: ; In the formula, Indicates the scratch depth, represents the calibration constant, represents the average gray value of the background area, Represents the average gray value of the scratch area.

[0062] What needs to be explained is: calibration constant It is adjusted according to actual conditions and the unit is depth / grayscale.

[0063] The functional expression of the stain area is as follows: ; In the formula, Represents the total stain area of ​​the mobile phone back cover image, Indicates the first The area of ​​the stain, Indicates the total number of stains on the image of the phone's back cover.

[0064] It needs to be explained that: the image of the back cover of the mobile phone is binarized by using image processing technology, and the area of ​​each stain is calculated. The area of ​​each stain is obtained by summing the number of pixels within the stain outline to obtain the total stain area on the image of the back cover of the mobile phone.

[0065] The functional expression of stain contrast is as follows: ; In the formula, represents the average stain contrast of the mobile phone back cover image, Indicates the first The contrast of the stains.

[0066] Among them, the image on the back cover of the mobile phone The contrast of each stain is represented by the standard deviation of the grayscale value of the mobile phone back cover image.

[0067] It should be explained that the color contrast between each stain and the surrounding area is analyzed by image processing technology, and the average value of the contrast of all stains is calculated to obtain the conspicuousness of the stain.

[0068] The function expression of edge smoothness is as follows: ; In the formula, Indicates the edge smoothness of the mobile phone back cover image. represents a constant, represents the variance of edge strength, Represents the smoothness threshold, which is used to adjust the influence of edge smoothness on the comprehensive judgment of the qualified state of the mobile phone back cover.

[0069] It needs to be explained that edge smoothness can be judged by the uniformity of edge strength, and edge strength is obtained from the edge strength map output by the edge detection algorithm. The value of each pixel in the edge strength map represents the edge strength of the point. The higher the edge strength, the more obvious the edge. The edge smoothness here is used to express the degree of deformation. When the edge smoothness is greater than the edge smoothing threshold, it means that the deformed edge may have irregularities and discontinuities.

[0070] The qualified state of the mobile phone back cover is comprehensively judged according to the generated results of scratch length, scratch depth, stain area, stain contrast and edge smoothness. The function expression for comprehensively judging the qualified state of the mobile phone back cover is as follows: ; In the formula, Indicates the qualification of the back cover of the mobile phone. represents the scratch length, Indicates the scratch depth, represents the scratch depth threshold, Represents the total stain area of ​​the mobile phone back cover image, Indicates the maximum stain area, represents the average stain contrast of the mobile phone back cover image, represents the stain contrast threshold, Indicates the edge smoothness of the mobile phone back cover image. Indicates the edge smoothing threshold.

[0071] Configure the qualification threshold, and generate the judgment result of the mobile phone back cover according to the comparison between the qualification of the mobile phone back cover and the qualification threshold. The rules for generating the judgment result include: If the qualification degree of the mobile phone back cover is less than or equal to the qualification threshold, it is displayed that the mobile phone back cover is qualified; If the qualification of the mobile phone back cover is greater than the qualification threshold, it is displayed that the mobile phone back cover is unqualified; After judging that the mobile phone back cover is unqualified, a label of the unqualified product is generated and transported to the unloading assembly 3 to distinguish between qualified and unqualified mobile phone back covers.

[0072] Example 2 In this embodiment, a method flow chart of an image processing method for high-speed detection of multiple surfaces of a mobile phone back cover is provided. Figure 2 As shown, an image processing method for high-speed detection of multiple surfaces of a mobile phone back cover includes: S1, receiving the back cover of the mobile phone and delivering it; S2, receiving the mobile phone back cover conveyed by the feeding assembly 1 and performing inspection; S3, identifying whether there is an abnormal area in the mobile phone back cover image generated during the detection process; S4, determining the abnormal type of the abnormal area, and generating the abnormal degree of the mobile phone back cover image; S5. Comprehensively judging the qualified state of the mobile phone back cover according to the generated result of the abnormality degree; S6. Classify according to the qualified status of the mobile phone back cover; The specific contents of an image processing method for high-speed detection of multiple surfaces of a mobile phone back cover can be found in an image processing system for high-speed detection of multiple surfaces of a mobile phone back cover, which will not be described in detail here.

[0073] Example 3 In this embodiment, a computer device is provided, including a memory and a processor, the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps of the image processing method for realizing the above-mentioned high-speed detection of multiple surfaces of the back cover of a mobile phone.

[0074] Example 4 In the present embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps of the above-mentioned image processing method for high-speed multi-surface detection of a mobile phone back cover are implemented.

[0075] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An image processing system for high-speed inspection of multiple surfaces of a mobile phone back cover, characterized in that: include: execution systems and processing systems; The execution system comprises a detection assembly (2), which is used to receive the back cover of the mobile phone and perform detection; The detection assembly (2) comprises a transmission electric cylinder (21), a front detection module (22), a conversion module (23) and a side detection module (24); the transmission electric cylinder (21) is used to place and transmit the mobile phone back cover to be detected; the front detection module (22) is fixedly arranged on one side of the conversion module (23) and, under the action of the transmission electric cylinder (21), transmits the mobile phone back cover to be detected for front detection of the mobile phone back cover; after the front detection, the mobile phone back cover is converted to the side detection module (24) through the conversion module (23); the side detection module (24) is fixedly arranged on the other side of the conversion module (23) and, under the action of the transmission electric cylinder (21), transmits the mobile phone back cover after the front detection for side detection of the mobile phone back cover; The processing system includes a visual inspection module; The visual inspection module is used to identify whether there is an abnormal area in the image of the back cover of the mobile phone, determine the abnormal type of the abnormal area, and generate the abnormality degree of the image of the back cover of the mobile phone. According to the generated result of the abnormality degree, the qualified state of the back cover of the mobile phone is comprehensively judged, and a non-conforming product label is generated.

2. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 1, characterized in that: The front inspection module (22) comprises a bright field camera (221), a front grating (222), a dark field camera (223) and an inclined plane grating (224); the bright field camera (221) is fixedly arranged above the transmission electric cylinder (21); the front grating (222) is fixedly arranged in the shooting direction of the bright field camera (221); the front grating (222) is used to cooperate with the bright field camera (221) to detect defects on the front of the back cover of the mobile phone; the dark field camera (223) is fixedly arranged above the transmission electric cylinder (21) and fixedly arranged on one side of the bright field camera (221); the inclined plane grating (224) is fixedly arranged in the shooting direction of the dark field camera (223); the inclined plane grating (224) is used to cooperate with the dark field camera (223) to detect defects on the front of the back cover of the mobile phone; The transmission electric cylinder (21) comprises a front inspection positioning jig (211), a transmission sliding seat (212) and a side inspection positioning jig (213). The transmission sliding seat (212) moves closer to or farther from the conversion module (23) under the drive of the transmission electric cylinder (21). The front inspection positioning jig (211) and the side inspection positioning jig (213) are used to place the back cover of the mobile phone to be inspected. The transmission sliding seat (212) is slidably connected to the front inspection positioning jig (211) and the side inspection positioning jig (213) respectively. When the back cover of the mobile phone is sucked out of the loading box (111), the moving electric cylinder (122) drives the material removal bracket (133) to move To the inspection assembly (2), the material picking bracket (133) is driven by the material picking electric cylinder (132) to move and be placed on the front inspection positioning jig (211), the transmission electric cylinder (21) drives the transmission sliding seat (212) to move along the length direction of the transmission sliding belt, and the front inspection positioning jig (211) is driven by the transmission sliding seat (212) to move to the conversion module (23), and the mobile phone back cover on the front inspection positioning jig (211) is sequentially inspected by the bright field camera (221) and the front grating (222) and the dark field camera (223) and the inclined grating (224), and a front image of the mobile phone back cover is comprehensively generated.

3. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 2, characterized in that: The conversion module (23) comprises a transfer pick-up and release cylinder (231) and a conversion electric cylinder (232), the conversion electric cylinder (232) being connected to the transfer pick-up and release cylinder (231), and the conversion electric cylinder (232) being used to control the transfer pick-up and release cylinder (231) to move toward or away from the transmission electric cylinder (21). The side inspection module (24) comprises a side grating (241) and a side scanning camera (242), the side scanning cameras (242) being respectively fixed on both sides of the transmission electric cylinder (21), the side gratings (241) being respectively fixed on both sides of the transmission electric cylinder (21) and fixed above the side scanning camera (242), the side gratings (241) being used to cooperate with the side scanning camera (242) to detect defects on the side of the mobile phone back cover, and the mobile phone back cover on the side inspection positioning jig (213) is detected by the side scanning camera (242) and the side grating (241) to generate a side image of the mobile phone back cover.

4. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 3, characterized in that: The front of the mobile phone back cover is detected by a combination of a front grating (222) and a bright field camera (221) and a combination of an inclined grating (224) and a dark field camera (223), and the side of the mobile phone back cover is detected by a combination of a side grating (241) and a side scanning camera (242), and the front image and the side image of the mobile phone back cover are respectively captured to generate a mobile phone back cover image, identify whether an abnormal area appears in the mobile phone back cover image, determine the abnormal type of the abnormal area, and generate the abnormal degree of the mobile phone back cover image where the abnormal area appears. The abnormal degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness, and comprehensively judge the qualified state of the mobile phone back cover according to the generated result of the abnormal degree to generate a judgment result of the mobile phone back cover.

5. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 4, characterized in that: The logic of identifying whether an abnormal area appears in the image of the back cover of the mobile phone includes: Calculate the grayscale co-occurrence matrix of the mobile phone back cover image, analyze the contrast, homogeneity and correlation of the grayscale co-occurrence matrix, configure the contrast threshold, homogeneity threshold and correlation threshold, and compare the contrast threshold, homogeneity threshold and correlation threshold with the contrast, homogeneity and correlation of the grayscale co-occurrence matrix of the mobile phone back cover image to determine whether there is an abnormal area in the mobile phone back cover image.

6. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 5, characterized in that: The function expression of the gray level co-occurrence matrix of the mobile phone back cover image is as follows: ； In the formula, Represents grayscale value and The frequency of pixel pairs co-appearing in the image of the mobile phone back cover, Indicates that the image of the phone's back cover is at position The gray value at and Indicates the relative position between adjacent pixels.

7. An image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 6, characterized in that: The function expression of whether the image of the back cover of the mobile phone has an abnormal area is as follows: ； In the formula, Indicates whether the image of the back cover of the mobile phone has an abnormal area. 1 indicates that the image of the back cover of the mobile phone has an abnormal area, and 0 indicates that the image of the back cover of the mobile phone has no abnormal area. Represents the contrast of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the contrast threshold, Represents the homogeneity of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the homogeneity threshold, Represents the correlation of the gray-level co-occurrence matrix of the mobile phone back cover image, represents the correlation threshold, Indicates situations other than the above.

8. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 7, characterized in that: The logic of determining the abnormal type of the abnormal area includes: If the image of the back cover of the mobile phone is of extreme contrast value and base homogeneity value, it is determined that the abnormal type of the abnormal area is stain; If the image of the back cover of the mobile phone is an extreme value of contrast and correlation, it is determined that the abnormal type of the abnormal area is a scratch; If the image of the back cover of the mobile phone is an extreme value of contrast, a base value of homogeneity, and an extreme value of correlation, then the abnormal type of the abnormal area is determined to be deformation.

9. The image processing system for high-speed multi-surface inspection of a mobile phone back cover as claimed in claim 8, characterized in that: The abnormality degree of the mobile phone back cover image with the abnormal area is generated, and the abnormality degree includes scratch length, scratch depth, stain area, stain contrast and edge smoothness. The qualified state of the mobile phone back cover is comprehensively judged according to the generated result of the abnormality degree. The function expression for comprehensively judging the qualified state of the mobile phone back cover is as follows: ； In the formula, Indicates the qualification of the back cover of the mobile phone. represents the scratch length, Indicates the scratch depth, represents the scratch depth threshold, Represents the total stain area of ​​the mobile phone back cover image, Indicates the maximum stain area, represents the average stain contrast of the mobile phone back cover image, represents the stain contrast threshold, Indicates the edge smoothness of the mobile phone back cover image. represents the edge smoothing threshold; Configure the pass threshold, and generate the judgment result of the mobile phone back cover according to the comparison between the pass degree of the mobile phone back cover and the pass threshold. The rules for generating the judgment result include: If the qualification of the mobile phone back cover is less than or equal to the qualification threshold, it is displayed that the mobile phone back cover is qualified; If the qualification degree of the mobile phone back cover is greater than the qualification threshold, the mobile phone back cover is displayed as unqualified and a label of unqualified product is generated.

10. An image processing method for high-speed detection of multiple surfaces of a mobile phone back cover, implemented based on an image processing system for high-speed detection of multiple surfaces of a mobile phone back cover according to any one of claims 1 to 9, characterized in that: include: S1, receiving the back cover of the mobile phone and delivering it; S2, receiving the mobile phone back cover conveyed by the feeding assembly (1) and performing inspection; S3, identifying whether there is an abnormal area in the mobile phone back cover image generated during the detection process; S4, determining the abnormal type of the abnormal area, and generating the abnormal degree of the mobile phone back cover image; S5. Comprehensively judging the qualified state of the mobile phone back cover according to the generated result of the abnormality degree; S6. Classify according to the qualified status of the mobile phone back cover.

11. A computer device, characterized in that: include: A memory for storing instructions; The processor is used to execute the instructions so that the computer device executes the image processing method for high-speed multi-faceted detection of a mobile phone back cover as described in claim 10.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the image processing method for high-speed multi-surface detection of a mobile phone back cover as described in claim 10 is implemented.

Images