Defect detection model updating method and device, electronic equipment and storage medium

By updating the model by selecting image samples with specific defects or large feature differences from POY textiles, the problem of poor detection performance of existing models is solved, and the model achieves high efficiency, adaptability and accuracy.

CN116188399BActive Publication Date: 2026-11-10BEIJING BAIDU NETCOM SCI & TECH CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202310041658.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-01-11
Publication Date
2026-11-10
Estimated Expiration
2043-01-11

AI Technical Summary

Technical Problem

Existing defect detection models based on deep learning algorithms do not perform well in POY textiles and are difficult to adapt to changes in process technology. Defect detection is complex and diverse.

Method used

Sample images are selected by acquiring defect detection results, and the model is updated based on feature information. Images with specific defects or large feature differences are selected as samples, and interactive annotation tools are used to optimize the model, thereby improving the model's generalization ability and iterative update efficiency.

Benefits of technology

This improved the quality and efficiency of model iteration and updates, enabling it to adapt to changes in the POY process in a timely manner and accurately detect various defects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116188399B_ABST
    Figure CN116188399B_ABST
Patent Text Reader

Abstract

The present disclosure provides a defect detection model updating method and device, electronic equipment and storage medium, relates to the technical field of artificial intelligence, in particular to the fields of deep learning, image processing and computer vision. The specific implementation scheme is: obtaining a plurality of defect detection results respectively output by a first defect detection model for a plurality of POY images; selecting a plurality of first sample images from the plurality of POY images based on the plurality of defect detection results; selecting a second sample image from the plurality of first sample images based on the feature information of each first sample image in the plurality of first sample images; updating the first defect detection model based on the second sample image to obtain a second defect detection model. The present disclosure enables the model to adapt to changes in the POY process in a timely manner, improves the defect detection effect, and accurately detects various defects in the POY product.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to the fields of deep learning, image processing and computer vision. Background Technology

[0002] POY (Pre-Oriented Yarn) is produced from polyester filaments through high-speed spinning. DTY (Draw Textured Yarn) can be produced by post-processing POY, including texturing, false twisting, and texturing. Due to the high spinning speed, large full-wound weight, and large full-wound diameter, POY exhibits complex and diverse defects, making external inspection of POY difficult and labor-intensive.

[0003] In related technologies, defect detection models based on deep learning algorithms can be used to detect and classify POY appearance defects. However, due to the complexity and diversity of defects in POY, and the emergence of different types of defects with process improvements, the detection effectiveness of defect detection models still needs to be improved. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for updating a defect detection model.

[0005] According to one aspect of this disclosure, a method for updating a defect detection model is provided, comprising:

[0006] Obtain multiple defect detection results output by the first defect detection model for multiple POY images;

[0007] Based on multiple defect detection results, multiple first sample images are selected from multiple POY images;

[0008] Based on the feature information of each of the multiple first sample images, a second sample image is selected from the multiple first sample images;

[0009] Based on the second sample image, the first defect detection model is updated to obtain the second defect detection model.

[0010] According to another aspect of this disclosure, an apparatus for updating a defect detection model is provided, comprising:

[0011] The acquisition module is used to acquire multiple defect detection results output by the first defect detection model for multiple POY images respectively;

[0012] The first selection module is used to select multiple first sample images from multiple POY images based on multiple defect detection results;

[0013] The second selection module is used to select a second sample image from the multiple first sample images based on the feature information of each first sample image in the multiple first sample images;

[0014] The update module is used to update the first defect detection model based on the second sample image to obtain the second defect detection model.

[0015] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] The memory is communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described in the present disclosure.

[0019] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the methods according to embodiments of this disclosure.

[0020] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods according to embodiments of this disclosure.

[0021] In the technical solution of this embodiment, after the first defect detection model outputs multiple defect detection results for multiple POY images, multiple first sample images are selected using the defect detection results, and then second sample images are selected based on the feature information of each first sample image. Based on this, this embodiment selects second sample images valuable for model updating from a large number of POY images according to the defect detection results and the feature information of each sample image. This not only improves the sample quality of model iteration updates but also improves the efficiency of a single iteration update, enabling the model to adapt to changes in the POY process in a timely manner, improving the defect detection effect, and accurately detecting various defects in POY products.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1This is a schematic diagram of an exemplary application scenario of the defect detection model update method according to an embodiment of this disclosure;

[0025] Figure 2 This is a flowchart illustrating a method for updating a defect detection model according to an embodiment of this disclosure;

[0026] Figure 3 This is a flowchart illustrating a method for updating a defect detection model according to another embodiment of this disclosure;

[0027] Figure 4 This is a schematic block diagram of an update device for a defect detection model provided in an embodiment of this disclosure;

[0028] Figure 5 This is a schematic block diagram of an updating device for a defect detection model provided in another embodiment of this disclosure;

[0029] Figure 6 This is a schematic block diagram of an electronic device used to implement the defect detection model update method of the embodiments of this disclosure. Detailed Implementation

[0030] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] To facilitate understanding of the defect detection model update method of this disclosure, the application scenarios of the method will be described below by way of example. Figure 1 This diagram illustrates an exemplary application scenario of the defect detection model update method according to an embodiment of the present disclosure. In this application scenario, an image acquisition device 10 (e.g., a camera, etc.) deployed in an external inspection device for POY products is used to acquire POY images. The image acquisition device 10 can be connected to a defect detection device 20 to send the POY images to the defect detection device 20. The defect detection device 20 processes the POY images using a pre-trained defect detection model to obtain defect detection results. The defect detection results may include information such as the location of the defect in the POY image, the size of the defect, and the number of defects, and may also include the POY image displaying defect detection boxes.

[0032] According to the method of this disclosure embodiment, in this application scenario, a defect detection model update device 30 is set up. The update device 30 can acquire POY images and corresponding defect detection results, select a portion of the acquired POY images for model updating, and then deploy the updated defect detection model in the defect detection device 20. In practical applications, the update device 30 and the defect detection device 20 can be as follows: Figure 1 The independent devices shown can also be different program modules deployed on the same device or in the same cluster.

[0033] Figure 2 A schematic flowchart illustrating an embodiment of the defect detection model update method provided in this disclosure is shown. This method can be applied to... Figure 1 The device shown is an update apparatus for the defect detection model, but is not limited thereto. Exemplarily, this apparatus can be deployed on electronic devices. Electronic devices are, for example, terminals, servers, or other processing devices in a standalone, multi-machine, or cluster system. Figure 2 As shown, the method may include:

[0034] Step S210: Obtain multiple defect detection results output by the first defect detection model for multiple POY images;

[0035] Step S220: Based on multiple defect detection results, select multiple first sample images from multiple POY images;

[0036] Step S230: Select a second sample image from the multiple first sample images based on the feature information of each first sample image in the multiple first sample images;

[0037] Step S240: Based on the second sample image, update the first defect detection model to obtain the second defect detection model.

[0038] In this embodiment of the disclosure, the first defect detection model can be a model used to detect defects such as lint, oil stains, snags, or knots on POY products. For example, the second defect detection model can be an updated version of the first defect detection model, and can be used to detect the same type of defects. For instance, both the second and first defect detection models can be used to detect lint, or both can be used to detect oil stains.

[0039] For example, the multiple POY images processed by the first defect detection model can be images of POY products on an external inspection device. This external inspection device can be integrated with an automated POY packaging line to perform online appearance defect detection of the spools during the automated packaging process. This external inspection device can be equipped with image acquisition devices, light sources, etc., to facilitate the acquisition of images of POY products on the automated packaging line, i.e., the aforementioned POY images.

[0040] For example, multiple defect detection results include the defect detection results for each POY image. These defect detection results may include information such as the location of the defect in the POY image, the size of the defect, the number of defects, the shape of the defect, and the type of defect, and may also include the POY image containing the defect detection bounding box.

[0041] For example, in step S220 above, a POY image with inaccurate defect detection results can be selected from multiple POY images as the first sample image to improve the detection capability of the first defect detection model through re-annotation and learning. Alternatively, based on the defect detection results, a POY image containing a specific morphology of defect can be selected from multiple POY images as the first sample image to specifically enhance the model's detection capability for that type of defect. For instance, if a new POY process is prone to producing looped fuzz, a POY image containing looped fuzz can be selected from multiple POY images based on the defect detection results.

[0042] For example, in step S230 above, multiple first sample images with significantly different features can be selected as multiple second sample images based on the feature information of each first sample image, so as to use the second sample images with significantly different features for learning and improve the generalization ability of the model.

[0043] As can be seen, this embodiment selects sample images sequentially based on defect detection results and feature information of each sample image, thereby identifying valuable second sample images for model updates from a large number of POY images. Since the POY appearance inspection scenario involves a complex and diverse range of defects and a high data production speed—specifically, far exceeding the data annotation speed—selecting valuable second sample images for model updates and using these images to update the model not only improves the sample quality of iterative model updates but also significantly increases the efficiency of each iteration. This allows the model to adapt promptly to changes in the POY process, improving defect detection effectiveness and accurately detecting various defects in POY products.

[0044] Figure 3 A flowchart illustrating an update method for a defect detection model provided in another embodiment of this disclosure is shown. Figure 3 As shown, the method includes:

[0045] Step S310: Obtain multiple defect detection results output by the first defect detection model for multiple POY images;

[0046] Step S320: Based on multiple defect detection results, select multiple first sample images from multiple POY images;

[0047] Step S330: Based on the feature information of each of the multiple first sample images, select a second sample image from the multiple first sample images;

[0048] Step S340: Based on the second sample image, update the first defect detection model to obtain the second defect detection model;

[0049] Step S350: Using the second defect detection model, process the POY image acquired by the image acquisition device in the POY product external inspection equipment to obtain the defect detection result of the POY image.

[0050] For example, when a second defect detection model is obtained through updating, the second defect detection model is used to replace the first defect detection model, and the POY images subsequently acquired by the image acquisition device are processed. Optionally, the second defect detection model can also be used as a new first defect detection model, thereby iterating through the above steps S310 to S350 and updating the defect detection model used in the POY product appearance inspection scenario multiple times.

[0051] This embodiment uses the updated second defect detection model to process online POY products, so that the defect detection effect of the actual products can adapt to the changes in the POY process in a timely manner and accurately detect various defects in POY products.

[0052] Optionally, in some embodiments of this disclosure, the first defect detection model is obtained by updating the third defect detection model based on the third sample image. The above-mentioned selection of multiple first sample images from multiple POY images based on the multiple defect detection results may include: determining multiple images with target defects from the multiple POY images based on the multiple defect detection results; wherein the target defects have different morphologies from the defects in the third sample images; and using the multiple images with target defects as the multiple first sample images.

[0053] In other words, images with defects that have different morphology from the third sample images used in previous training are selected as the first sample images.

[0054] For example, the selection of the first sample image can be achieved through human-computer interaction. For instance, the defect detection results of multiple POY images can be shown to the user, and then multiple images with the target defect can be identified from the multiple POY images based on the user's input. That is, combining manual methods can improve the accuracy of the judgment and thus improve the quality of sample selection.

[0055] According to the above embodiments, when a new type of defect appears in the POY product appearance inspection scenario, the POY image corresponding to the defect can be selected to obtain a sample image for updating the defect detection model. This allows the model to adapt to the complex and diverse changes in POY product defects in a timely manner, thereby improving the model's defect detection accuracy.

[0056] Optionally, in some embodiments, selecting a second sample image from the plurality of first sample images based on the feature information of each of the plurality of first sample images includes: clustering the plurality of first sample images based on the feature information of each of the plurality of first sample images to obtain a plurality of image clusters; and selecting a subset of images from each of the plurality of image clusters to obtain the second sample image.

[0057] For example, a self-supervised model can be used to process each first sample image to obtain the feature information of each first sample image. Then, multiple first sample images are clustered in the feature space, so that first sample images with similar feature information distances are in the same cluster, and first sample images with larger feature information distances are in different clusters. Thus, by selecting a portion of images in each image cluster, some similar images are filtered out, resulting in multiple second sample images with a certain distance between them.

[0058] For example, one or more images that have the smallest sum of distances to every other image in each image cluster can be selected as the second sample image in that image cluster. This second sample image can also be called a salient sample.

[0059] According to the above embodiments, by clustering, sample images can be selected based on the distance between images, maximizing the distance between different second sample images used for model updates, thereby enhancing the value of the second sample images in model updates, and thus driving model iteration with high-quality samples.

[0060] Optionally, in some embodiments, updating the first defect detection model based on the second sample image to obtain a second defect detection model includes: annotating defects in the second sample image using an interactive segmentation annotation tool to obtain annotation information of the second sample image; and updating the first defect detection model based on the second sample image and the annotation information to obtain the second defect detection model.

[0061] For example, the annotation information can be annotated defect detection boxes. In the first defect detection model, the corresponding defect detection result can be obtained based on the second sample image. Then, the loss can be calculated based on the annotation information and the defect detection result. The first defect detection model can be updated using the loss to obtain the second defect detection model.

[0062] According to the above embodiments, using an interactive segmentation and annotation tool to annotate defects in the second sample image can reduce the manual and time costs of data annotation and improve the efficiency of model iteration and update.

[0063] According to embodiments of this disclosure, this disclosure also provides an apparatus for updating a defect detection model. Figure 4 A schematic block diagram of an apparatus for updating a defect detection model according to an embodiment of this disclosure is shown. Figure 4 As shown, the device may include:

[0064] The acquisition module 410 is used to acquire multiple defect detection results output by the first defect detection model for multiple POY images respectively;

[0065] The first selection module 420 is used to select multiple first sample images from multiple POY images based on multiple defect detection results;

[0066] The second selection module 430 is used to select a second sample image from the multiple first sample images based on the feature information of each first sample image in the multiple first sample images;

[0067] The update module 440 is used to update the first defect detection model based on the second sample image to obtain the second defect detection model.

[0068] Figure 5 A schematic block diagram of an apparatus for updating a defect detection model according to another embodiment of this disclosure is shown. Figure 5 As shown, the defect detection model update device includes an acquisition module 510, a first selection module 520, a second selection module 530, and an update module 540. The functions of each module are as described in the previous embodiment and will not be repeated here. In this embodiment, the first defect detection model is obtained by updating the third defect detection model based on the third sample image. Figure 5 As shown, the first selection module 520 may include:

[0069] The first image selection unit 521 is used to identify multiple images with target defects from multiple POY images based on multiple defect detection results; wherein the target defects have different shapes from the defects in the third sample image.

[0070] The determining unit 522 is used to take multiple images with target defects as multiple first sample images.

[0071] Optionally, such as Figure 5 As shown, the second selection module 530 may include:

[0072] Clustering unit 531 is used to cluster multiple first sample images based on the feature information of each first sample image in multiple first sample images to obtain multiple image clusters;

[0073] The second image selection unit 532 is used to select a portion of images in each of the multiple image clusters to obtain a second sample image.

[0074] Optionally, such as Figure 5 As shown, the update module 540 may include:

[0075] The annotation unit 541 is used to annotate defects in the second sample image based on the interactive segmentation annotation tool to obtain the annotation information of the second sample image;

[0076] The model update unit 542 is used to update the first defect detection model based on the second sample image and annotation information to obtain the second defect detection model.

[0077] Optionally, such as Figure 5 As shown, the update device for the defect detection model also includes:

[0078] Application module 550 is used to process POY images acquired by the image acquisition device in the POY product external inspection equipment using the second defect detection model, and obtain the defect detection results of the POY images.

[0079] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0080] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0081] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0082] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0083] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0084] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0085] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for updating a defect detection model. For example, in some embodiments, the method for updating a defect detection model can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method for updating a defect detection model described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method for updating a defect detection model by any other suitable means (e.g., by means of firmware).

[0086] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0088] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0090] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0091] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0092] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for updating a defect detection model, comprising: Obtain multiple defect detection results output by the first defect detection model for multiple pre-oriented POY images; Based on the multiple defect detection results, multiple images with target defects are identified from multiple POY images; wherein, the first defect detection model is obtained by updating the third defect detection model based on the third sample image, and the target defect has a different shape from the defect in the third sample image; the multiple images with target defects are used as multiple first sample images; Based on the feature information of each of the plurality of first sample images, the plurality of first sample images are clustered to obtain a plurality of image clusters; and a portion of images are selected from each of the plurality of image clusters to obtain second sample images; Based on the second sample image, the first defect detection model is updated to obtain the second defect detection model; The step of updating the first defect detection model based on the second sample image to obtain a second defect detection model includes: Defects in the second sample image are annotated using an interactive segmentation and annotation tool to obtain the annotation information of the second sample image; Based on the second sample image and the annotation information, the first defect detection model is updated to obtain the second defect detection model.

2. The method according to claim 1, further comprising: Using the second defect detection model, the POY images acquired by the image acquisition device in the POY product external inspection equipment are processed to obtain the defect detection results of the POY images.

3. An update device for a defect detection model, comprising: The acquisition module is used to acquire multiple defect detection results output by the first defect detection model for multiple POY images respectively; The first selection module is used to determine multiple images with target defects from multiple POY images based on the multiple defect detection results; wherein, the first defect detection model is obtained by updating the third defect detection model based on the third sample image, and the target defect has a different shape from the defect in the third sample image; the multiple images with target defects are used as multiple first sample images; The second selection module is used to cluster the multiple first sample images based on the feature information of each first sample image in the multiple first sample images to obtain multiple image clusters; and to select a portion of images in each of the multiple image clusters to obtain second sample images; The update module is used to update the first defect detection model based on the second sample image to obtain a second defect detection model; The update module includes: The annotation unit is used to annotate defects in the second sample image based on an interactive segmentation annotation tool, so as to obtain the annotation information of the second sample image; The model update unit is used to update the first defect detection model based on the second sample image and the annotation information to obtain the second defect detection model.

4. The apparatus according to claim 3, further comprising: The application module is used to process the POY images acquired by the image acquisition device in the POY product external inspection equipment using the second defect detection model, and obtain the defect detection results of the POY images.

5. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of claim 1 or 2.

6. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to claim 1 or 2.

7. A computer program product comprising a computer program that, when executed by a processor, implements the method according to claim 1 or 2.

Citation Information

Patent Citations

  • Defect detection method and apparatus and terminal equipment

    CN111060514A

  • Silk ingot appearance forming defect detection and grading method, storage medium and equipment

    CN114299065A

  • Detection method and system, equipment and storage medium

    CN114913110A