TWI780580B - Image reinspection method, computer device, and storage medium - Google Patents

Abstract

The present application provides an image reinspection method, a computer device, and a storage medium. The image reinspection method includes obtaining images to be tested and corresponding image information; using an artificial intelligence program to analyze the image information and obtain parameters of the image to be tested; using a pre-trained image retest model to retest the images to be tested based on the parameters and obtaining retest results; uploading the images to be tested with flaws in the retest results to a pre-established image re-inspection system; distributing the images to be tested to designated users using the pre-established image re-inspection system, receiving marks of the designated user for the images to be tested, and feeding back a final test result of the images to be tested according to the marks. This application can assist in the reinspection of printed circuit boards judged as defective by automatic optical inspection equipment, reduce labor costs, and improve inspection efficiency and accuracy.

Description

Image recheck method, computer device and storage medium

The invention relates to the field of printed circuit board detection, in particular to an image re-inspection method, a computer device and a storage medium.

Printed Circuit Board (PCB) is mostly inspected by Automated Optical Inspection (AOI) equipment during the manufacturing process, so as to determine whether the PCB contains defects such as deviation, missing parts, less tin, and more tin. Defective parts. Usually, due to the fact that there will be a large number of false defects in PCBs judged as defective products by AOI equipment, that is, it is difficult for AOI equipment to accurately detect only a small number of defective products. Manual re-inspection of defective PCBs takes a lot of manpower and time.

In view of the above, it is necessary to provide an image re-inspection method, computer device and storage medium, which can re-inspect printed circuit board PCBs judged as defective products by automatic optical inspection AOI equipment based on computer vision image processing technology, and reduce manual re-inspection. The detection workload is improved, and the detection efficiency and accuracy are improved.

The image re-inspection method includes: obtaining the image to be tested and the image information of the image to be tested, and the image to be tested is identified as a defective image in at least one detection; Analyzing the image information of the image to be tested to obtain the parameters of the image to be tested; Re-inspecting the image to obtain the re-inspection result of the image to be tested; when the re-inspection result indicates that the image to be tested has defects, uploading the image to be tested to the pre-established map in the computer device An image re-inspection system; distribute the image to be tested to designated users through the image re-inspection system, receive the designated user's mark on the image to be tested; and according to the image to be tested The marker returns the final detection result of the image to be tested.

Optionally, the image to be tested is a PCB image of a printed circuit board, the method scans the PCB with an automatic optical inspection (AOI) device to obtain the image to be tested, and uses the AOI device to scan the image to be tested Save in the preset path.

Optionally, the method further includes obtaining information of the PCB in the image to be tested.

Optionally, the method further includes: acquiring a preset number of flawless PCB images; performing image processing on the preset number of flawless PCB images; and using the processed flawless PCB The neural network is trained on images to obtain the image re-inspection model.

Optionally, the method further includes: using the artificial intelligence program to input parameters of the image to be tested into the image re-examination model.

Optionally, the method further includes: based on parameters of the image to be tested, using the image re-inspection model to obtain the image to be tested.

Optionally, the method further includes: using the image re-inspection model to input the parameters of the image to be tested and the re-inspection result into the artificial intelligence program; and using the artificial intelligence program to input the The parameters of the image to be tested and the retest results are stored in a pre-established database.

Optionally, the final detection result of the image to be tested includes: the image to be tested is a flawless image, or the image to be tested is a flawed image.

The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the image review method is implemented.

The computer device includes a memory and at least one processor, at least one instruction is stored in the memory, and the at least one instruction is executed by the at least one processor to realize the Describe the image re-examination method.

Compared with the known technology, the image re-inspection method, computer device and storage medium can re-inspect PCBs judged as defective products by AOI equipment based on computer vision image processing technology, reduce the workload of manual re-inspection, and improve detection efficiency and accuracy.

3: Computer device

32: Processor

31: Storage

33: Display

S1~S5: steps

In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the accompanying drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present application, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

Fig. 1 is a flowchart of an image re-examination method in a preferred embodiment of the present application.

FIG. 2 is a structural diagram of a computer device in a preferred embodiment of the present application.

In order to more clearly understand the above objects, features and advantages of the present application, the present application will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

A lot of specific details are set forth in the following description to facilitate a full understanding of the application, and the described embodiments are only a part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein in the specification of the application are only for the purpose of describing specific embodiments, and are not intended to limit the application.

Referring to FIG. 1 , it is a flowchart of an image re-examination method in a preferred embodiment of the present application.

In this embodiment, the image re-inspection method can be applied to a computer device (such as the computer device 3 shown in FIG. The image rechecking function provided by the application method may run on a computer device in the form of a software development kit (Software Development Kit, SDK).

As shown in FIG. 1 , the image re-examination method specifically includes the following steps. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

Step S1, the computer device obtains the image to be tested and the image information of the image to be tested, and the image to be tested is identified as a defective image in at least one inspection.

In one embodiment, the image to be tested is a printed circuit board (Printed Circuit Board, PCB) image, and the method uses an automatic optical inspection (Automated Optical Inspection, AOI) device to scan the PCB to obtain the image to be tested , and use the AOI device to save the image to be tested in a preset path.

It should be noted that the AOI device is a device that can scan products such as PCBs based on optical principles and detect common defects.

In one embodiment, the PCBs can come from different production lines. The production line refers to an assembly line composed of multiple devices required to produce the PCB. The multiple devices are arranged according to the sequence of the PCB manufacturing process to form a production line. production line. For example, the plurality of devices may include a board loading machine, a solder paste printing machine, a high-speed placement machine, a high-precision placement machine, a reflow oven, etc. The board loading machine is the equipment required for the first process of manufacturing PCBs, and other equipment After the board loading machine is arranged in sequence, the reflow oven is arranged at the last position of the production line. The production lines can be distinguished by different numbers, for example, the different production lines can be numbered as 01, 02, etc. by using ordered two-digit numbers.

In one embodiment, when the AOI equipment is used to scan and detect the PCB produced in the production line, a one-to-one mode is adopted, and one AOI equipment corresponds to one production line. Multiple (eg, 20) AOI devices can be used simultaneously to scan PCBs produced by multiple (eg, 20) production lines and detect images of the PCBs to obtain detection results of the PCB images. E.g, Different AOI equipment can be numbered as AOI001, AOI002, etc. in the format of AOI+ordered three-digit number, and AOI001 can be placed behind the reflow furnace of No. Inspection; at the same time, place AOI002 behind the reflow furnace of No. 02 production line, and use AOI002 to scan and inspect the PCB produced by No. 02 production line.

In one embodiment, the AOI equipment detects the image of the PCB, and the obtained detection results include: the image of the PCB is a defect image, and the image of the PCB is a defect-free image. The flaw image is an image of a PCB that is judged to contain flaws by the AOI equipment, for example, the AOI equipment judges the image of a PCB containing defective components such as offset, missing parts, less tin, and more tin as flaws image.

In one embodiment, the image to be tested is an image of a PCB detected as a defect image by the AOI equipment, and the image to be tested is an image to be re-inspected.

In one embodiment, the AOI device only saves the image to be tested, and saves the image to be tested in a preset path, for example, the AOI device numbered AOI001 can save the detected image The image to be tested is saved in the pre-established folder Download001 in the local path.

In one embodiment, the computer device obtains the information of the PCB in the image to be tested.

In one embodiment, the information of the PCB includes a product number of the PCB. Specifically, the different PCBs can be numbered as PCB0001, PCB0002, etc. with sequential four-digit numbers.

In one embodiment, the information about the PCB further includes information about the production line that produces the PCB, for example, the production line corresponding to the PCB numbered PCB0001 is No. 01 production line.

In one embodiment, the information of the PCB further includes the production time of the PCB, for example, the production time of the PCB numbered PCB0001 is 09:30:05. It should be noted that the time may also include information such as year, month, and day, which will not be described in detail in examples.

In one embodiment, the image information of the image to be tested includes the machine information of the AOI equipment corresponding to the image to be tested, for example, the AOI equipment numbered AOI001 will be the image of the PCB numbered PCB0001 If it is judged as the image to be tested, then the machine information of the AOI equipment corresponding to the image to be tested of the PCB numbered PCB0001 is AOI001.

In one embodiment, the image information of the image to be tested also includes the name of the image to be tested, for example, the AOI equipment numbered AOI001 uses the image of the PCB numbered PCB0001 as the image to be tested When saving, the image to be tested can be named PCB0001.jpg. It should be noted that when the number of the PCB is used as the name of the image to be tested of the corresponding PCB, the name of the image to be tested may not need to be stored in the image information of the image to be tested. Let's talk about it again.

In one embodiment, the image information of the image to be tested also includes the storage path of the image to be tested, for example, the AOI equipment numbered AOI001 saves the image to be tested PCB0001.jpg in the file folder Download001 .

In one embodiment, the AOI device saves the relevant data of the image to be tested in a preset path, for example, the AOI device numbered AOI001 can use Extensible Markup Language (XML) to save the image to be tested Mark and define the relevant information of the image, and save the obtained ".xml" format document in the local path, and name it File001.xml. In other embodiments, the related materials of the image to be tested may also be saved in a file in ".txt" format.

It should be noted that, taking a single AOI device as an example, for example, for the AOI device numbered AOI001, only one folder Download001 can be generated to save the image to be tested, and only one file File001.xml (or File001. txt) to save the relevant information of the image to be tested. At this time, the machine information of the AOI equipment corresponding to the image to be tested may not be stored in the image information of the image to be tested, and will not be described in detail later.

In one embodiment, the document File001.xml can save the relevant information of multiple (for example, 300) images to be tested obtained by the AOI equipment numbered AOI001, and the number is AOI001 The AOI equipment can mark and define each information in the relevant data of the image to be tested in the file File001.xml, and save the relevant data of each image to be tested correspondingly. For example, the AOI equipment numbered AOI001 can save the relevant information of each image to be tested in sequence (for example, from left to right or from top to bottom) in the file File001 according to the time sequence in which each image to be tested is obtained. .xml in a column or row. It should be noted that when each information in the relevant data of each image to be tested is stored in a row or a column, it may be out of order.

Step S2, the computer device uses an artificial intelligence program to analyze the relevant data of the image to be tested to obtain parameters of the image to be tested.

In one embodiment, the computer device can use an artificial intelligence (AI) program to obtain relevant data of the image to be tested, analyze the relevant data of the image to be tested, and obtain the image to be tested parameters. For example, the AI program is used to obtain the file File001.xml, and the file File001.xml stores the relevant data of the image to be tested obtained by using the AOI device numbered AOI001. Use the AI program to parse the relevant data in the XML format in the file File001.xml into database (such as SQL Server) parameters, and import the database parameters into the database for storage. It should be noted that the AI program can obtain multiple documents and analyze the multiple documents at the same time. When the document obtained by the AI program is File001.txt in ".txt" format, File001.txt can be converted into Documents in other formats (such as ".xml" format), and then analyze the data in the converted documents.

In one embodiment, the parameters of the image to be tested are the image information of the image to be tested and the information of the PCB, for example, the image of the PCB numbered PCB0001 is the image to be tested, and its parameters It is: Download001 (storage path of PCB image), 01 (production line of PCB), PCB0001 (number of PCB), 09:30:05 (production time of PCB). It should be noted that the format of the parameters of the image to be tested is a database parameter.

In one embodiment, after the computer device uses the AI program to import the parameters of the image to be tested into the database, the database will identify and analyze the parameters of the image to be tested, and analyze the parameters according to preset rules. After the parameters of the image to be tested are sorted. For example, the default The rule of can be: the first parameter is the production time of the PCB, the second parameter is the production line of the PCB, the third parameter is the storage path of the image to be tested, and the fourth parameter is the serial number of the PCB. For example, the image of the PCB numbered PCB0001 is the image to be tested, and the SQL Server can sort the parameters of the image to be tested as follows: 09:30:05,01,Download001,PCB0001.

In one embodiment, the computer device uses the AI program to input the parameters into the image review model. For example, the AI program invokes an application programming interface (Application Programming Interface, API) to pass parameters of the image to be tested into the image re-inspection model. It should be noted that when the image re-inspection model receives the parameters of the image to be tested imported by the AI program by calling the API, it also receives an instruction to perform image re-inspection to perform image re-inspection.

Step S3 , the computer device uses the pre-trained image re-inspection model to re-inspect the image-to-be-tested based on the parameters of the image-to-be-tested, and obtain the re-inspection result of the image-to-be-tested image.

In one embodiment, the pre-trained image re-inspection model refers to: a computer device acquires a preset number of flawless PCB images; image processing is performed on the preset number of flawless PCB images and using the processed image of the flawless PCB to train a neural network to obtain the image re-inspection model.

In one embodiment, the preset number of defect-free PCB images may be a small number (for example, 200) of defect-free PCB images. It should be noted that, due to the low defect rate of the PCB in the actual production process, a large number of defect-free PCB images can be easily obtained, and the staff can use the pre-established image re-inspection system in step S4 to obtain all the images. The preset number of flawless PCB images.

In one embodiment, the image processing of the preset number of flawless PCB images includes: analyzing the graphics elements of the flawless PCB images, and calculating the RGB (red color) of the images. (R), green (G), blue (B)) and grayscale, divide the similar regions of the graphic elements in the image into the same region, separate the image into different regions, and locate the components of the PCB in the described position in the image, select the area where each component is located, and use the fuzzy algorithm to Noise reduction is performed on the image of each region mentioned above, and unimportant regions are eliminated. It should be noted that the methods used for image processing of the preset number of flawless PCB images are common methods in the field of image processing, and the specific process will not be repeated here.

In one embodiment, the neural network may be a convolutional neural network (Convolutional Neural Networks, CNN), and the computer device may use the preset number of flawless PCB images to train the CNN to generate the image complex. check model. In one embodiment, the image re-inspection model can be copied, installed in the AOI equipment corresponding to each production line, and detect the image to be inspected obtained by the corresponding AOI equipment. In one embodiment, there is no difference between different image re-inspection models installed in different AOI devices, and can be replicated and installed in different types of AOI devices to run.

In one embodiment, the computer device uses the image re-examination model to obtain the image to be tested based on the parameters of the image to be tested.

In one embodiment, the image re-examination model can determine the storage path of the image to be tested based on parameter three such as Download001, such as the folder Download001, and determine the storage path of the image to be tested based on parameter four such as PCB0001 The name of the image is, for example, PCB0001.jpg, and the image in the storage path, such as the folder Download001, such as PCB0001.jpg is copied to the local path to obtain the image to be tested.

In one embodiment, the image re-inspection model is essentially an image defect detection model, and using the image re-inspection model to re-inspect the image to be tested is to re-inspect the image to be tested like flaw detection. The image re-inspection model can determine the location of each component in the PCB board in the image to be tested, and compare it with the corresponding area of the flawless image of the PCB, according to preset rules (for example, the graphics elements are all square error reaches a preset threshold) to obtain the re-inspection result of the image to be tested.

In one embodiment, the re-inspection results of the image to be tested include: the image to be tested is an image with blemishes, and the image to be tested is an image without blemishes. It should be noted that due to the defect of AOI equipment, only a small part (for example, accounting for 4%) of the image to be tested Like an image that actually has blemishes. By using the image re-inspection model to re-inspect the image to be tested, images that actually have defects can be detected from the image to be tested.

In one embodiment, the computer device can use the image re-inspection model to input the parameters of the image to be tested and the re-inspection result into the AI program; and use the AI program to input the image to be tested The image parameters and the re-examination results are stored in a pre-established database (such as SQL Server).

Step S4. When the re-inspection result indicates that the image to be tested has defects, the computer device uploads the image to be tested to a pre-established image re-inspection system in the computer device.

In one embodiment, the image re-inspection system can acquire the image to be tested based on the parameters of the defective image.

In one embodiment, the image re-inspection system can obtain the parameters of the image to be tested that the reinspection result is a defect from the database, and display the image to be tested on the image In the interface of the review system. For example, after the image re-inspection system recognizes that the re-inspection result of the PCB image numbered PCB0001 in the database is flawed, the image to be tested can be determined based on the parameter three Download001 of the PCB image numbered PCB0001 The storage path of the image is the folder Download001. Based on the parameter four PCB0001 of the PCB image numbered PCB0001, the image name of the image to be tested is determined as PCB0001.jpg, and the image PCB0001.jpg in the folder Download001 is determined. displayed in the system interface. For example, the interface can display the re-inspection results as flawed images to be tested page by page, the interface can display 5 images to be tested per page, a total of 20 pages, and the 20th page can display less than 5 images to be tested.

Step S5, the computer device distributes the image to be tested to designated users through the image re-examination system, receives the designated user's mark on the image to be tested, and according to the mark of the image to be tested Feedback the final detection result of the image to be tested.

In one embodiment, the image re-inspection system can distribute the image to be tested that has defects in the re-inspection result to different designated users, and the designated user will mark the image to be tested, The user has permission to log in to the image re-inspection system to operate the work personnel. For example, the image re-inspection system can distribute the image to be tested to users corresponding to the type of the image to be tested according to the type of the image to be tested; it can also be randomly distributed; it can also be Distribution is performed according to the number of images currently to be processed by the user (for example, the number of unmarked images to be tested), until all the images to be tested are distributed.

In one embodiment, the final detection result of the image to be tested includes: the image to be tested is a flawless image, or the image to be tested is a flawed image.

In one embodiment, the specified user marks the image to be tested through different buttons or icons to determine the final detection result of the image to be tested. For example, the staff can log in to the image re-inspection system, and mark the images to be tested on the interface of the image re-inspection system, and there can be two options under each image to be tested. Buttons: "pass" and "ng", use the "pass" button to mark flawless images, and the "ng" button to mark flawed images. When the staff determines that the image to be tested is a flawless image, they can click the "pass" button to mark it, or when the staff determines that the image to be tested is a flawed image, they can click "ng" button to mark it. It should be noted that the preset number of flawless PCB images acquired in step S2 are the images obtained by using the method described here and marked with the "pass" button by the staff.

In one embodiment, the computer device can use the image review system to save the images marked as "pass" and "ng" respectively.

In other embodiments, after all the re-inspection results of the images to be tested with defects are marked by the staff, the computer device will display the images to be tested marked as "ng" on the image In the interface of the re-examination system, the parameters of the image to be tested are displayed below the image to be tested. For example, when the image of PCB numbered PCB0001 is marked as "ng" by the staff, PCB0001.jpg can be displayed in the interface, and 09:30:05,01, Download001, PCB0001, It is convenient for the staff to check and adjust the equipment in the No. 01 production line that produces PCB0001.

The above-mentioned Fig. 1 has introduced the image re-inspection method of the present application in detail, below in conjunction with Fig. 2, for The hardware device architecture for implementing the image re-examination method is introduced.

It should be understood that the embodiments are only for illustration, and are not limited by the structure in terms of the scope of the patent application.

Referring to FIG. 2 , it is a schematic structural diagram of a computer device provided by a preferred embodiment of the present application. In a preferred embodiment of the present application, the computer device 3 includes a storage 31 , at least one processor 32 , and a display 33 . Those skilled in the art should understand that the structure of the computer device shown in Figure 2 does not constitute a limitation of the embodiment of the present application, it can be a bus-type structure or a star structure, and the computer device 3 can also include a ratio More or less other hardware or software, or different arrangements of components are illustrated.

In some embodiments, the computer device 3 includes a terminal capable of automatically performing numerical calculations and/or information processing according to preset or stored instructions, and its hardware includes but not limited to microprocessors, dedicated integrated circuits, Programmable gate arrays, digital word processors and embedded devices, etc.

It should be noted that the computer device 3 is only an example, and other existing or future electronic products that can be adapted to this application should also be included in the scope of protection of this application and included here by reference.

In some embodiments, the storage 31 is used to store program codes and various data, and realize high-speed and automatic access to programs or data during the operation of the computer device 3 . The memory 31 includes a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable Read-Only Memory, PROM), an erasable programmable read-only memory (Erasable Programmable Read -Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM) , CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, disk storage, tape storage, or any other computer-readable storage medium that can be used to carry or store data.

In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions. , including one or more central processing units (Central Processing unit, CPU), microprocessors, digital signal processing chips, graphics processors and combinations of various control chips. The at least one processor 32 is the control core (Control Unit) of the computer device 3, and uses various interfaces and lines to connect the various components of the entire computer device 3, by running or executing the program code stored in the memory 31 Or modules, and call the data stored in the storage 31 to execute various functions of the computer device 3 and process data, such as the function of performing image review.

In some embodiments, with reference to FIG. 1 , the storage 31 in the computer device 3 stores computer-readable instructions to implement an image review method, and the processor 32 can execute the computer-readable instructions to implement The image recheck method.

In some embodiments, the display 33 may be a display device capable of displaying images capable of touch screen operations, for example, the display 33 may be used to display the interface of the image review system.

Although not shown, the computer device 3 may also include a power supply (such as a battery) for supplying power to each component. Preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, thereby realizing Manage functions such as charging, discharging, and power management. The power supply may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components. The computer device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

It should be understood that the embodiments are only for illustration, and are not limited by the structure in terms of the scope of the patent application. In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and the implementation In actual implementation, there may be another division method.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or may also be distributed to multiple networks on the unit. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented not only in the form of hardware, but also in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, no matter from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the application is defined by the appended claims rather than the above description, so it is intended to All changes within the meaning and range of equivalents of the elements are embraced in this application. Any reference sign in a claim should not be construed as limiting the claim to which it relates. Furthermore, it is clear that the word "comprising" does not exclude other elements or the singular does not exclude the plural. A plurality of units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to denote names and do not imply any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application without limitation. Although the present application has been described in detail with reference to the above preferred embodiments, those of ordinary skill in the art should understand that the present application can be The technical solution shall be modified or equivalently replaced without departing from the spirit and scope of the technical solution of the present application.

S1~S5: steps

Claims (10)

An image re-inspection method applied to a computer device, wherein the method includes: obtaining an image to be tested and image information of the image to be tested, and the image to be tested is identified in at least one detection is a defective image, the image information of the image to be tested also includes a storage path and an image name of the image to be tested; the image information of the image to be tested is saved in a preset path, Including: using Extensible Markup Language XML to mark and define the image information of the image to be tested, and saving the obtained document in xml format in a local path, and the document in xml format is used to save the image to be tested The image information of the image to be tested; using the artificial intelligence program to analyze the image information of the image to be tested to obtain the parameters of the image to be tested, including: using the artificial intelligence program to obtain the xml format document, analyzing the image information in the XML format in the document in the xml format into database parameters, and importing the database parameters into the database for preservation; using the artificial intelligence program to call an application programming development interface API, Input the parameters into the pre-trained image re-inspection model, use the image re-inspection model to re-inspect the image to be tested based on the parameters of the image to be tested, and obtain the image to be tested The re-inspection result includes: using the image re-inspection model to obtain the image to be tested according to the storage path and the image name of the image to be tested; when the reinspection result indicates that the image to be tested When there is a defect in the image to be tested, upload the image to be tested to the pre-established image re-inspection system in the computer device; distribute the image to be tested to designated users through the image re-inspection system, receiving the designated user's mark on the image to be tested, and feeding back a final detection result on the image to be tested according to the mark on the image to be tested. The image re-inspection method according to claim 1, wherein the image to be tested is a printed circuit board PCB image, and the method uses automatic optical inspection AOI equipment to scan the PCB to obtain the image to be tested, and uses The AOI equipment saves the image to be tested in a preset path. The image re-examination method as described in claim 2, wherein the method also includes obtaining Information about the PCB in the image to be tested. The image re-inspection method according to claim 1, wherein the method further includes: acquiring a preset number of flawless PCB images; performing image processing on the preset number of flawless PCB images, Including: analyzing the graphic elements of the flawless PCB image, calculating the RGB red, green, blue and gray scale of the image, dividing the areas with similar graphic elements in the image into the same area, and separating the images into different areas, locate the position of each component of the PCB in the image, frame the area where each component is located, and use a fuzzy algorithm to denoise the image of each area; and use the processed The flawless PCB image trains a neural network to obtain the image re-inspection model. The image re-inspection method according to claim 1, wherein the method further includes: using the artificial intelligence program to input parameters of the image to be tested into the image re-inspection model. The image re-inspection method according to claim 1, wherein the method further includes: based on the parameters of the image-to-be-tested, using the image re-inspection model to obtain the image-to-be-tested. The image re-inspection method according to claim 1, wherein the method further includes: using the image re-inspection model to input the parameters of the image to be tested and the re-inspection results into the artificial intelligence program ; and using the artificial intelligence program to save the parameters of the image to be tested and the re-examination results in a pre-established database. The image re-inspection method according to claim 1, wherein the final detection result of the image to be tested includes: the image to be tested is a flawless image, or the image to be tested is a flawed image . A computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the image re-examination according to any one of claims 1 to 8 is realized method. A computer device, wherein the computer device includes a memory and at least one processor, at least one instruction is stored in the memory, and the at least one instruction is executed by the at least one The processor implements the image re-examination method according to any one of claims 1 to 8 when executed.

Images