CN116206111B - Defect identification method and device, electronic equipment and storage medium - Google Patents
Defect identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116206111B CN116206111B CN202310214302.8A CN202310214302A CN116206111B CN 116206111 B CN116206111 B CN 116206111B CN 202310214302 A CN202310214302 A CN 202310214302A CN 116206111 B CN116206111 B CN 116206111B
- Authority
- CN
- China
- Prior art keywords
- defect
- image
- key point
- pixel points
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 53
- 230000011218 segmentation Effects 0.000 claims abstract description 50
- 239000011159 matrix material Substances 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 abstract description 5
- 238000011156 evaluation Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a defect identification method, a defect identification device, electronic equipment and a storage medium. The labeling consistency evaluation method provided by the invention comprises the following steps: acquiring a target image of a defect to be detected; inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image; selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points; taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image; and inputting each local image into a trained semantic segmentation model to obtain the defect position in the local image. According to the labeling consistency evaluation method, the key point detection model is used for positioning the defect center point, and then the local image containing the defect is intercepted by taking the defect center point as the center, so that the area occupation ratio of the defect in the local image is greatly improved, and the defect can be identified by the subsequent semantic segmentation model.
Description
Technical Field
The present invention relates to the field of deep learning technologies, and in particular, to a defect identification method, device, electronic apparatus, and storage medium.
Background
Various types of defects occur in industrial processes, which affect product quality or even raise safety problems, and are usually detected and identified by computational vision techniques. The semantic segmentation algorithm for deep learning belongs to a classification algorithm at pixel level, which can predict whether each pixel in an image belongs to a defect. The semantic segmentation is used for classifying pixels, so that data required by industries such as defect positions, areas and the like can be accurately output, and the prediction accuracy is high and the stability is high, so that the method is widely applied to industrial appearance defect detection and identification.
However, the semantic segmentation algorithm has a disadvantage that the semantic segmentation algorithm does not have very high recognition accuracy in any situation, and the semantic segmentation algorithm is more obvious in an industrial quality inspection scene, because the size of an image shot by an industrial camera in industrial quality inspection is usually particularly large, the size of a target defect is particularly small, and at the moment, the semantic segmentation model is often difficult to recognize the small target defect, so that missing is caused.
Aiming at the problem of missing the small target defect, common solutions are as follows: 1) Increasing the number of positive samples in the training data; 2) The parameter scale of the semantic segmentation algorithm network is increased so as to enable the model to have stronger learning ability; 3) More and more abundant data amplification methods are used in the model training process.
However, 1) training data is difficult to collect, can be resolved not a half a time, and is economically costly, and in addition, increasing the number of positive samples is not necessarily effective in solving the problem of missing a small target defect. 2) The increase of the parameter scale of the semantic segmentation algorithm network means that more training data are needed, the model training speed of a large network is low, more hardware resources are needed, and the cost of the method is high. 3) Even if more and richer data amplification methods are used in the model training process, the method still can treat the symptoms but not the root cause, and the problem of missing the small target defect is difficult to effectively solve.
Disclosure of Invention
Based on the above, the invention aims to provide a defect identification method, a defect identification device, electronic equipment and a storage medium, which are used for automatically calculating an evaluation index, acquiring information of consistency of a plurality of data labeling results and timely guiding and improving quality of data labeling, so that model accuracy is improved.
In a first aspect, the present invention provides a defect identification method, including the steps of:
acquiring a target image of a defect to be detected;
inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image;
selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
and inputting each local image into a trained semantic segmentation model to obtain the defect position in the local image.
Further, the training process of the keypoint detection model comprises the following steps:
collecting a plurality of original images containing defects to be identified;
for each original image, marking each defect to be inspected in the original image as a key point by using a key point marking tool to obtain a marked image;
and training the key point detection model by using a plurality of the target images to obtain a trained key point detection model.
Further, the keypoint detection model is a deep model.
Further, the training process of the semantic segmentation model comprises the following steps:
collecting a plurality of original images containing defects to be identified;
inputting a plurality of original images into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the original images;
for each original image, selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
marking the position of the defect to be detected in each partial image by using a segmentation marking tool to obtain marked partial images;
and training the semantic segmentation model by using the plurality of marked local images to obtain a trained semantic segmentation model.
Further, the semantic segmentation model is a deeplapV3 algorithm network.
Further, the local image is square.
Further, n is a positive integer between 3 and 5.
In a second aspect, the present invention also provides a defect identifying apparatus, including:
the target image acquisition module is used for acquiring a target image of the defect to be detected;
the confidence coefficient matrix acquisition module is used for inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image;
the central point acquisition module is used for selecting n pixel points with the maximum confidence coefficient from the confidence coefficient matrix and acquiring coordinates of the pixel points;
the local image intercepting module is used for intercepting n local images in the target image by taking the coordinates of the n pixel points as the center;
and the defect identification module is used for inputting each partial image into the trained semantic segmentation model to obtain the defect position in the partial image.
In a third aspect, the present invention also provides an electronic device, including:
at least one memory and at least one processor;
the memory is used for storing one or more programs;
the one or more programs, when executed by the at least one processor, cause the at least one processor to implement the steps of a defect identification method according to any of the first aspects of the present invention.
In a fourth aspect, the present invention also provides a computer-readable storage medium,
the computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of a defect identification method according to any of the first aspects of the invention.
According to the defect identification method, the device, the electronic equipment and the storage medium, the key point detection model with global searching capability is used for positioning the defect center point, N points with highest confidence are used as the defect-containing areas, so that the defect detection rate is greatly improved, and the problem that small target defects possibly are missed in the conventional method is solved. The method comprises the steps of firstly positioning a defect center point by using a key point detection model, and then taking the defect center point as a center to intercept a square image containing the defect, so that the area occupation ratio of the defect in a square screenshot is greatly improved, the defect can be easily identified by a subsequent semantic segmentation model, and the detection rate of the semantic segmentation model on the small target defect is greatly improved.
For a better understanding and implementation, the present invention is described in detail below with reference to the drawings.
Drawings
FIG. 1 is a schematic diagram illustrating steps of a defect identifying method according to the present invention;
FIG. 2 is a flow chart of training and using a keypoint detection model in one embodiment;
FIG. 3 is a flow diagram of training and using a semantic segmentation model according to one embodiment;
fig. 4 is a schematic structural diagram of a defect identifying device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the embodiments of the present application, are within the scope of the embodiments of the present application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims. In the description of this application, it should be understood that the terms "first," "second," "third," and the like are used merely to distinguish between similar objects and are not necessarily used to describe a particular order or sequence, nor should they be construed to indicate or imply relative importance. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be.
Furthermore, in the description of the present application, unless otherwise indicated, "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
In view of the problems in the background art, an embodiment of the present application provides a defect identifying method, as shown in fig. 1 to 3, including the following steps:
s01: and obtaining a target image of the defect to be detected.
In a specific application scenario, the target image is obtained by shooting a product with a defect to be detected by the image acquisition equipment. Defects to be detected generally refer to detecting flaws on the surface of an article, such as blemishes, scratches, pits, shallow bumps, edge defects, pattern defects, spots, dimples, color differences, flaws, insufficient material, excessive material, and the like.
Specifically, character recognition and character defect detection on the surface of the electronic equipment can be included; detecting defects on the surface of the liquid crystal display, such as flaws, flaws and scratches; detecting defects in the paper making process, such as stains, spots and impurities, in the paper making industry; detecting defects such as stains, chromatic aberration and the like of the printed matter; and (3) checking the printing quality of the bottle cap, and identifying bar codes and characters on the product package.
The defects are all presented on the surface of the product and can be visually distinguished by human eyes. Further, machine vision detection can be performed by capturing images of the surface of the product.
S02: and inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image.
The key point detection model is trained and used for identifying defect key points in the image, the input of the key point detection model is an original image of a defect to be detected, and the output of the key point detection model is a confidence matrix with the same size as the input image. The numerical value of each element represents the confidence that the corresponding pixel point belongs to the center point of the defect to be detected in the input graph, and the larger the numerical value is, the greater the probability that the point is the center point of the defect is.
S03: and selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points.
As described above, a larger confidence value represents a greater likelihood that the point is the center point of the defect. Therefore, a proper number of pixels with the highest confidence can be selected for subsequent defect detection and confirmation according to actual industrial production requirements.
Too few choices are easy to cause error and leakage of defects, and too many choices increase the calculated amount and cause resource waste. In a specific embodiment, the present invention selects n to be a positive integer between 3 and 5.
S04: and taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image.
In a specific application scenario, in order to facilitate interception and calculation, the local image is generally set to be rectangular, and more preferably, the local image is square. The side length of the partial image can be set according to the maximum size of the defect to be detected, for example, the whole set is 200, so long as the square area is ensured to contain the defect to be detected.
S05: and inputting each local image into a trained semantic segmentation model to obtain the defect position in the local image.
Semantic segmentation is an important direction in computer vision. Unlike object detection and recognition, semantic segmentation enables classification at the image pixel level. It is able to divide a picture or video (which is actually a picture if the video is extracted in frames) into a plurality of blocks according to the difference in category.
In a specific embodiment, the semantic segmentation model used by the invention has the input of a square defect screenshot and the output of a binary image, and the prospect of the binary image indicates the position of the defect to be detected.
According to the defect identification method provided by the invention, the large graph is not directly used for establishing the semantic segmentation model, but is combined with the key point detection algorithm, and the characteristic of globally searching the target object by using the key point detection algorithm is utilized to improve the detection rate of small target defects.
In a preferred embodiment, the keypoint detection model in the present invention is the deep model.
The training process for the keypoint detection model comprises the steps of:
s021: a plurality of original images containing defects to be identified are collected.
S022: and marking each defect to be inspected in the original image as a key point by using a key point marking tool for each original image to obtain a marked image.
S023: and training the key point detection model by using a plurality of the target images to obtain a trained key point detection model.
In another preferred embodiment, the semantic segmentation model is a deeplapV3 algorithm network.
The training process for the semantic segmentation model comprises the following steps:
s031: collecting a plurality of original images containing defects to be identified;
s032: inputting a plurality of original images into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the original images;
s033: for each original image, selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
s034: taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
s035: marking the position of the defect to be detected in each partial image by using a segmentation marking tool to obtain marked partial images;
s03: and training the semantic segmentation model by using the plurality of marked local images to obtain a trained semantic segmentation model.
According to the defect identification method, the whole processing process is split into two steps based on the trained key point detection model and the semantic segmentation model: the first step is to locate all possible positions of the target by using a key point detection model, and to perform small-range screenshot; the segmentation algorithm of the second step is responsible for identifying the target from the screenshot of step one.
The embodiment of the present application further provides a defect identifying device, as shown in fig. 4, the labeling consistency evaluating device 400 includes:
an image acquisition module 401, configured to acquire a plurality of image sets, where each image set includes a plurality of annotation images, and each annotation image includes an annotation frame;
the marking image scoring module 402 is configured to compare gray values of pixel points at both sides inside and outside the marking frame for each marking image to obtain a first gray difference value, and score the marking image according to the first gray difference value;
the score average calculation module 403 is configured to obtain, for each image set, a score average of the image set according to the score of each of the labeled images in the image set;
a difference value calculation module 404, configured to calculate a difference value between the score average values of the plurality of image sets;
and the evaluation result determining module 405 is configured to obtain defect identification results between different image sets according to the gap value.
Preferably, the training process of the keypoint detection model comprises the following steps:
collecting a plurality of original images containing defects to be identified;
for each original image, marking each defect to be inspected in the original image as a key point by using a key point marking tool to obtain a marked image;
and training the key point detection model by using a plurality of the target images to obtain a trained key point detection model.
Preferably, the keypoint detection model is a deep model.
Preferably, the training process of the semantic segmentation model comprises the following steps:
collecting a plurality of original images containing defects to be identified;
inputting a plurality of original images into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the original images;
for each original image, selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
marking the position of the defect to be detected in each partial image by using a segmentation marking tool to obtain marked partial images;
and training the semantic segmentation model by using the plurality of marked local images to obtain a trained semantic segmentation model.
Preferably, the semantic segmentation model is a deeplapV3 algorithm network.
Preferably, the local image is square.
Preferably, n is a positive integer between 3 and 5.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The embodiment of the application also provides electronic equipment, which comprises:
at least one memory and at least one processor;
the memory is used for storing one or more programs;
the one or more programs, when executed by the at least one processor, cause the at least one processor to implement the steps of a defect identification method as previously described.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The above-described apparatus embodiments are merely illustrative, wherein the components illustrated as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Embodiments of the present application also provide a computer-readable storage medium,
the computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of a defect identification method as described above.
Computer-usable storage media include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of random access memory (R AM), read only memory (R O M), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by the computing device.
According to the defect identification method, the device, the electronic equipment and the storage medium, the key point detection model with global searching capability is used for positioning the defect center point, N points with highest confidence are used as the defect-containing areas, so that the defect detection rate is greatly improved, and the problem that small target defects possibly are missed in the conventional method is solved. The method comprises the steps of firstly positioning a defect center point by using a key point detection model, and then taking the defect center point as a center to intercept a square image containing the defect, so that the area occupation ratio of the defect in a square screenshot is greatly improved, the defect can be easily identified by a subsequent semantic segmentation model, and the detection rate of the semantic segmentation model on the small target defect is greatly improved.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (8)
1. A defect identification method, comprising the steps of:
acquiring a target image of a defect to be detected;
inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image;
selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
inputting each partial image into a trained semantic segmentation model to obtain a defect position in the partial image;
the training process of the key point detection model comprises the following steps of:
collecting a plurality of original images containing defects to be identified;
for each original image, marking each defect to be inspected in the original image as a key point by using a key point marking tool to obtain a marked image;
training the key point detection model by using a plurality of marked images to obtain a trained key point detection model;
the training process of the semantic segmentation model comprises the following steps of:
collecting a plurality of original images containing defects to be identified;
inputting a plurality of original images into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the original images;
for each original image, selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points;
taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image;
marking the position of the defect to be detected in each partial image by using a segmentation marking tool to obtain marked partial images,
and training the semantic segmentation model by using the plurality of marked local images to obtain a trained semantic segmentation model.
2. A defect identification method according to claim 1, wherein:
the key point detection model is a deep model.
3. A defect identification method according to claim 2, wherein:
the semantic segmentation model is a deeplapV3 algorithm network.
4. A defect identification method according to claim 1, wherein:
the partial image is square.
5. The defect identification method of claim 4, wherein:
n is a positive integer between 3 and 5.
6. A defect recognition apparatus, comprising:
the target image acquisition module is used for acquiring a target image of the defect to be detected;
the confidence coefficient matrix acquisition module is used for inputting the target image into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the target image;
the central point acquisition module is used for selecting n pixel points with the maximum confidence coefficient from the confidence coefficient matrix and acquiring coordinates of the pixel points;
the local image intercepting module is used for intercepting n local images in the target image by taking the coordinates of the n pixel points as the center;
the defect identification module is used for inputting each local image into the trained semantic segmentation model to obtain the defect position in the local image;
the key point detection model training module: for collecting a plurality of original images containing defects to be identified; for each original image, marking each defect to be inspected in the original image as a key point by using a key point marking tool to obtain a marked image; training the key point detection model by using a plurality of marked images to obtain a trained key point detection model;
semantic segmentation model training module: for collecting a plurality of original images containing defects to be identified; inputting a plurality of original images into a trained key point detection model to obtain a confidence coefficient matrix corresponding to the original images; for each original image, selecting n pixel points with the maximum confidence in the confidence matrix, and acquiring coordinates of the pixel points; taking the coordinates of the n pixel points as the center, and intercepting n partial images in the target image; and marking the position of the defect to be detected in each local image by using a segmentation marking tool to obtain marked local images, and training the semantic segmentation model by using a plurality of marked local images to obtain a trained semantic segmentation model.
7. An electronic device, comprising:
at least one memory and at least one processor;
the memory is used for storing one or more programs;
when executed by the at least one processor, causes the at least one processor to implement the steps of a defect identification method as claimed in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized by:
the computer readable storage medium stores a computer program which, when executed by a processor, implements the steps of a defect identification method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310214302.8A CN116206111B (en) | 2023-03-07 | 2023-03-07 | Defect identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310214302.8A CN116206111B (en) | 2023-03-07 | 2023-03-07 | Defect identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116206111A CN116206111A (en) | 2023-06-02 |
| CN116206111B true CN116206111B (en) | 2024-02-02 |
Family
ID=86511024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310214302.8A Active CN116206111B (en) | 2023-03-07 | 2023-03-07 | Defect identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116206111B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598084A (en) * | 2020-05-11 | 2020-08-28 | 北京阿丘机器人科技有限公司 | Defect segmentation network training method, device and equipment and readable storage medium |
| CN111862092A (en) * | 2020-08-05 | 2020-10-30 | 复旦大学 | Express delivery outer package defect detection method and device based on deep learning |
| CN112767369A (en) * | 2021-01-25 | 2021-05-07 | 佛山科学技术学院 | Defect identification and detection method and device for small hardware and computer readable storage medium |
| CN113763355A (en) * | 2021-09-07 | 2021-12-07 | 创新奇智(青岛)科技有限公司 | Defect detection method and device, electronic equipment and storage medium |
| CN113781391A (en) * | 2021-08-02 | 2021-12-10 | 南京中科创达软件科技有限公司 | Image defect detection method and related equipment |
| CN115527050A (en) * | 2022-11-29 | 2022-12-27 | 南方科技大学 | Image feature matching method, computer device and readable storage medium |
-
2023
- 2023-03-07 CN CN202310214302.8A patent/CN116206111B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598084A (en) * | 2020-05-11 | 2020-08-28 | 北京阿丘机器人科技有限公司 | Defect segmentation network training method, device and equipment and readable storage medium |
| CN111862092A (en) * | 2020-08-05 | 2020-10-30 | 复旦大学 | Express delivery outer package defect detection method and device based on deep learning |
| CN112767369A (en) * | 2021-01-25 | 2021-05-07 | 佛山科学技术学院 | Defect identification and detection method and device for small hardware and computer readable storage medium |
| CN113781391A (en) * | 2021-08-02 | 2021-12-10 | 南京中科创达软件科技有限公司 | Image defect detection method and related equipment |
| CN113763355A (en) * | 2021-09-07 | 2021-12-07 | 创新奇智(青岛)科技有限公司 | Defect detection method and device, electronic equipment and storage medium |
| CN115527050A (en) * | 2022-11-29 | 2022-12-27 | 南方科技大学 | Image feature matching method, computer device and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116206111A (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179225B (en) | Test paper surface texture defect detection method based on gray gradient clustering | |
| WO2021143343A1 (en) | Method and device for testing product quality | |
| CN106934800B (en) | Metal plate strip surface defect detection method and device based on YOLO9000 network | |
| CN114140679A (en) | Defect fusion method, device, recognition system and storage medium | |
| CN106290392A (en) | A kind of little micro-bearing surface pitting defects online test method and system thereof | |
| CN112308854B (en) | Automatic detection method and system for chip surface flaws and electronic equipment | |
| CN113780087B (en) | Postal package text detection method and equipment based on deep learning | |
| CN116030016A (en) | Product image defect detection method and device, electronic equipment and storage medium | |
| CN112330598A (en) | Method and device for detecting stiff silk defects on chemical fiber surface and storage medium | |
| CN113850749A (en) | Method for training defect detector | |
| CN111415343A (en) | Artificial intelligence-based six-side appearance detection method for chip multilayer ceramic capacitor | |
| CN117115171B (en) | Slight bright point defect detection method applied to subway LCD display screen | |
| CN116206111B (en) | Defect identification method and device, electronic equipment and storage medium | |
| CN116681677A (en) | Lithium battery defect detection method, device and system | |
| CN115546139A (en) | Defect detection method and device based on machine vision and electronic equipment | |
| CN115457563A (en) | Zero-missing-detection and low-error-identification ship water gauge reading method | |
| CN111507177B (en) | Identification method and device for metering turnover cabinet | |
| CN104517114B (en) | A kind of element characteristics recognition methods and system | |
| CN114119594A (en) | Oil leakage detection method and device based on deep learning | |
| CN113112513A (en) | Method and device for AI (artificial intelligence) recognition of banded tissue, computer equipment and storage medium | |
| CN111524102A (en) | Method and device for detecting screen contamination of liquid crystal display | |
| CN111563869A (en) | Stain testing method for quality inspection of camera module | |
| CN117495846B (en) | Image detection method, device, electronic equipment and storage medium | |
| CN114898148B (en) | Egg offset detection method and system based on deep learning | |
| CN115272310B (en) | Method and device for detecting defects of workpiece |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 101-301, Building 3, No. 9, Huijiang South 2nd Road, Dashi Street, Panyu District, Guangzhou City, Guangdong Province, 5114300 Patentee after: Guangzhou Yihong Intelligent Equipment Co.,Ltd. Country or region after: Zhong Guo Address before: Room 101-301, Building 3, No. 9, Huijiang South 2nd Road, Dashi Street, Panyu District, Guangzhou City, Guangdong Province, 5114300 Patentee before: GUANGZHOU EHOLLY INTELLIGENT EQUIPMENT Co.,Ltd. Country or region before: Zhong Guo |