CN115240031A - Method and system for generating plate surface defects based on generation countermeasure network - Google Patents
Method and system for generating plate surface defects based on generation countermeasure network Download PDFInfo
- Publication number
- CN115240031A CN115240031A CN202210859013.9A CN202210859013A CN115240031A CN 115240031 A CN115240031 A CN 115240031A CN 202210859013 A CN202210859013 A CN 202210859013A CN 115240031 A CN115240031 A CN 115240031A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- defect detection
- background image
- generation
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 238
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 133
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000013507 mapping Methods 0.000 claims abstract description 25
- 238000012795 verification Methods 0.000 claims abstract description 23
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 11
- 239000000463 material Substances 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 230000003042 antagnostic effect Effects 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 238000007689 inspection Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000013078 crystal Substances 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002023 wood Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 239000007888 film coating Substances 0.000 description 1
- 238000009501 film coating Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004579 marble Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- -1 offset Substances 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Images
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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of machine learning, in particular to a method and a system for generating a plate surface defect based on generation of a countermeasure network, aiming at solving the problem that the prior art is difficult to obtain enough training samples and causes poor detection precision of a defect detection model, and the technical scheme is a method for generating a plate surface defect based on generation of the countermeasure network, which comprises the following steps: acquiring an original plate image, and separating the original plate image into a background image set and a defect feature set; identifying pattern features of each sample in the background image set, classifying the background image set into at least one pattern domain based on the pattern features; constructing a mapping relation between a pattern domain and defect characteristics; synthesizing the background image set and the defect feature set into a training set and a verification set according to a mapping relation; the defect detection model is trained and obtained based on the training set, and the effect of the model is verified based on the verification set.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to a method and a system for generating surface defects of a plate based on a generated confrontation network.
Background
Industrial automation refers to the general term for machine equipment or production processes to perform measurement, manipulation, etc. information processing and process control according to the intended objective without the need for direct manual intervention. The automation technology is a method and technology for exploring and researching an automation process, and is a comprehensive technology relating to the technical fields of machinery, microelectronics, computers, machine vision and the like. Due to the need for an industrial revolution, automated technology has been vigorously developed. Meanwhile, automation technology also promotes the progress of industry, and nowadays, automation technology is widely applied to the fields of machine manufacturing, electric power, construction, information technology and the like, and becomes a main means for improving labor productivity.
The surface layer of the floor, i.e. the floor or floor of a house, made of wood or other materials, is an important component of the appearance of the building, and in the floor industry, especially in the field of PVC floors, the appearance has a great influence on the quality evaluation of the floor products and the purchase desire of the consumers, so that the quality inspection of the appearance of the floor becomes an important part in the production process of the floor.
At present, in the process of detecting the surface defects of the floor boards, the floor images with the surface defects can be generally used as training samples to train an artificial intelligent model, and finally, the trained model is used for detecting the surface defects of the floor to be detected.
In the process of implementing the present application, the inventors found that the above-mentioned technology has at least the following problems:
before the model is actually put into use, a large number of floor images with surface defects need to be obtained as training samples, and the problem that the finally obtained model has poor defect detection accuracy is easily caused because enough training samples are difficult to obtain under actual conditions.
Disclosure of Invention
In order to expand the sample sources of the surface defect detection model and reduce the number of invalid samples, thereby improving the accuracy of the surface defect detection result, the application provides a method and a system for generating the surface defect of the plate based on the generation countermeasure network.
In a first aspect, the application provides a method for generating a surface defect of a plate based on a generated countermeasure network, which adopts the following technical scheme:
a method for generating surface defects of a sheet material based on generation of a countermeasure network, the method comprising the steps of:
acquiring an original plate image, and separating the original plate image into a background image set and a defect feature set;
identifying pattern features of each sample in the background image set, classifying the background image set into at least one pattern domain based on the pattern features;
performing material analysis on the background image based on the pattern domain, and constructing a mapping relation between the pattern domain and the defect characteristics based on the material analysis result;
synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relation through a preset image generation model;
and training and acquiring a defect detection model based on the defect detection sample set.
By adopting the technical scheme, the background image and the defect characteristics on the original plate image are separated, which is beneficial to respectively obtaining the background image set and the defect characteristic set, so that the defect characteristics originally fixed on a certain specific background can be synthesized on other background images, which is beneficial to expanding the number of samples finally used for training the defect detection model.
In a specific implementation manner, before the synthesizing, by using a preset image generation model, the background image set and the defect feature set into a defect detection sample set according to the mapping relationship, the method further includes:
generating a training sample set and a verification sample set based on the pre-acquired original plate image;
and training a preset initial confrontation network generation model through the training sample set and the verification sample set to obtain the image generation model.
By adopting the technical scheme, the training sample set and the verification sample set are generated through the original plate image, the training of the image generation model through the training sample set and the verification sample set is facilitated, the generation of the model through the countermeasure network is facilitated, different background images and style characteristics in the original plate image are synthesized, wherein the style characteristics, namely the defect characteristics, are facilitated to improve the image synthesis efficiency, and meanwhile, the number of samples for training the defect detection model is facilitated to be increased.
In a specific implementation manner, after the synthesizing, by using a preset image generation model, the background image set and the defect feature set into a defect detection sample set according to the mapping relationship, the method further includes:
generating a feedback training sample set and a feedback verification sample set based on the defect detection sample set;
training and updating the image generation model through the feedback training sample set and the feedback verification sample set;
replacing the initial image generation model with the updated image generation model.
By adopting the technical scheme, after the initial image generation model is obtained, in the process of using the initial image model for image generation, the generated defect detection sample set is used as a training sample and fed back to the initial image generation model for training, so that the efficiency and the generation quality of the image generation model for image generation are further improved, and the accuracy of defect detection is further improved.
In a specific embodiment, the method further comprises:
generating a random background image based on the material characteristics;
and supplementing the random background image into the background image set, wherein the proportion of the random background image in a material domain corresponding to the background image set does not exceed a preset random threshold value.
By adopting the technical scheme, the random background images are generated based on the material characteristics, the number of training samples is further increased through the images generated artificially and randomly, meanwhile, the occupation ratio of the random background images in the background image set is limited, the effectiveness of the training samples is controlled, and the possibility of poor precision of a final defect detection model caused by excessive random background images is avoided.
In a specific possible embodiment, the method further comprises:
in the training process of the defect detection model, acquiring a graded defect detection model based on the number of defect detection samples used by the defect detection model;
and performing ascending arrangement on the graded defect detection models based on the number of the used defect detection samples, and connecting the graded defect detection models in series to form a defect detection system.
By adopting the technical scheme, in the process of training the defect detection model, the number of samples operated by the training model determines the precision of the training model, but a large number of training samples can also cause the low training efficiency of the defect detection model, so the defect detection model is obtained in a grading way, the defect detection model with proper precision can be obtained according to the requirement, the obtaining efficiency of the defect detection model is improved, the defect detection models with different precisions are connected in series to form the defect detection system, the defect detection system is used for detecting the plate image in a way that the precision is gradually increased, and the detection efficiency is improved while the precision of the detection result is ensured.
In a specific embodiment, the sorting the graded defect inspection models based on the number of defect inspection samples used and serially connected into the defect inspection system further includes:
acquiring an image of a plate to be detected, inputting the image of the plate to be detected into a defect detection system, and carrying out grading detection according to the arrangement sequence of the defect detection system;
and when the plate to be detected is detected to have surface defects in the image, stopping the defect detection and marking the plate to be detected as a defective product.
By adopting the technical scheme, the defect detection system is utilized to carry out detection of gradually increasing precision on the plate images, and the detection efficiency is improved while the precision of the plate detection efficiency is ensured.
In a specific implementation manner, after the acquiring an original plate image and separating the original plate image into a background image set and a defect feature set, the method further includes:
randomly adjusting the image parameters of the background image set and the defect feature set;
the random adjustment comprises a single image parameter adjustment and/or a combined adjustment of at least two image parameters.
By adopting the technical scheme, the image parameters in the background image set and the defect characteristic set are randomly adjusted, so that the sample number is favorably enlarged, the adjustment comprises single random adjustment and combination of multiple random adjustments, the range of adjustment operation is favorably enlarged, and the sample number is further enlarged.
In a second aspect, the present application provides a system for generating surface defects of a sheet based on a generated countermeasure network, which adopts the following technical solutions:
a system for generating sheet surface defects based on generation of a countermeasure network, the system comprising:
the system comprises an original image module, a defect feature set module and a defect feature set module, wherein the original image module is used for acquiring an original plate image and separating the original plate image into a background image set and the defect feature set;
the background classification module is used for identifying the material characteristics of each sample in the background image set and classifying the background image set into at least one material domain based on the material characteristics;
the characteristic mapping module is used for constructing a mapping relation between the material domain and the defect characteristics;
the sample synthesis module is used for synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relation through a preset image generation model;
and the detection model module is used for training and acquiring a defect detection model based on the defect detection sample set.
By adopting the technical scheme, the background image and the defect characteristics on the original plate image are separated, which is beneficial to respectively obtaining the background image set and the defect characteristic set, so that the defect characteristics originally fixed on a certain specific background can be synthesized on other background images, which is beneficial to expanding the sample number finally used for training the defect detection model.
In a third aspect, the present application provides an intelligent terminal, which adopts the following technical scheme:
an intelligent terminal comprising a processor and a memory, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement a method for generating a surface defect of a sheet based on a generation countermeasure network according to any one of the first aspect.
By adopting the technical scheme, the processor in the intelligent terminal can realize the plate surface defect generation method based on the generation countermeasure network according to the related computer program stored in the memory, so that the sample source of the surface defect detection model can be expanded, the number of invalid samples can be reduced, and the accuracy of the surface defect detection result can be improved.
In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement a method for generating defects on a surface of a sheet material based on generation of a countering network according to any one of the first aspects.
By adopting the technical scheme, the corresponding program can be stored, so that the sample source of the surface defect detection model can be enlarged, the number of invalid samples can be reduced, and the accuracy of the surface defect detection result can be improved.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the method is characterized in that a background image and defect characteristics on an original plate image are separated, which is beneficial to respectively obtaining a background image set and a defect characteristic set, so that the defect characteristics originally fixed on a certain specific background can be synthesized on other background images, which is beneficial to expanding the sample number finally used for training a defect detection model, in addition, the background image set is classified based on material characteristics, and the classified background image set and the defect characteristic set are mapped, which is beneficial to reducing the possibility that the defect characteristics which are not matched with the material of the background image appear when the defect detection sample is synthesized, thereby being beneficial to improving the effectiveness of the defect detection sample, and finally being beneficial to improving the accuracy of the defect detection model when in application;
2. the method comprises the steps that a training sample set and a verification sample set are generated through an original plate image, an image generation model is trained through the training sample set and the verification sample set, and the generation model is generated through an antagonistic network, so that different background images and style characteristics in the original plate image can be synthesized, wherein the style characteristics are also defect characteristics, the efficiency of image synthesis is improved, and the number of samples for training a defect detection model is expanded;
3. in the process of training the defect detection model, the number of samples operated by the training model determines the precision of the training model, but a large number of training samples can also cause the low training efficiency of the defect detection model, so the defect detection model is obtained in a grading manner, the defect detection model with proper precision can be obtained according to requirements, the obtaining efficiency of the defect detection model is improved, the defect detection models with different precisions are connected in series to form a defect detection system, the defect detection system is used for detecting the plate images in a mode that the precision is gradually increased, and the detection efficiency is improved while the precision of detection results is ensured.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for generating surface defects of a plate based on generation of a countermeasure network, which is shown in the embodiment of the application;
FIG. 2 is a system flow diagram of a system for generating surface defects of a sheet based on generation of a countermeasure network shown in an embodiment of the present application;
fig. 3 is a schematic structural diagram of the intelligent terminal shown in the embodiment of the present application.
Detailed Description
The present embodiments are only illustrative and not restrictive, and those skilled in the art can make modifications to the embodiments without inventive contribution as required after reading the present specification, but the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to fig. 1 to 3 of the embodiments of the present application as long as they are protected by patent laws within the scope of the claims of the present application to make the objects, technical solutions and advantages of the embodiments of the present application clearer, and it is obvious that the described embodiments are a part of the embodiments of the present application, but not all of the embodiments.
The embodiment of the application provides a method for generating surface defects of a plate based on a generated countermeasure network, which can be applied to the intelligent quality inspection process of the plate, wherein an execution main body can be an intelligent terminal and is assisted by a plate image acquisition device arranged on a quality inspection line.
The process flow shown in fig. 1 will be described in detail below with reference to specific embodiments, and the contents may be as follows:
In implementation, the intelligent terminal acquires an original plate image, where the original plate image may be a real plate image directly acquired by a technician through an image acquisition device, and the real plate image includes a plate image with and without surface defects. After the original plate image is obtained, the intelligent terminal can deduct the defect image in the original plate image, then mark the defect image by combining the defect information, and finally store the defect image as the defect characteristic. Therefore, the intelligent terminal can integrate the acquired defect characteristics into a defect characteristic set, and can also store the plate images without defects and the plate images without surface defects into background images after the defect images are extracted and integrate the plate images into the background image set.
At this time, the intelligent terminal can acquire the background image set and the defect image set of the plate, so that the defect image is not fixed on a specific plate.
In one embodiment, in order to expand the number of training samples, the following processing steps may be further included after step 101: randomly adjusting the image parameters of the background image set and the defect feature set; the random adjustment comprises a single image parameter adjustment and/or a combined adjustment of at least two image parameters.
Specifically, the stochastic processing may include one or more of brightness adjustment, contrast adjustment, flip adjustment, rotation adjustment, and gaussian noise perturbation.
This contributes to the enlargement of the sample size based on the existing material by means of arithmetic.
In implementation, after the intelligent terminal obtains the background image set, the pattern features of each sample in the background image set can be extracted, and the background image set is classified into a plurality of pattern domains based on the pattern features. Specifically, the intelligent terminal may compare the texture features of the background image sample with preset pattern features by extracting the texture features of the background image sample, mark the background image sample with the material features having the highest similarity to the texture features, and after marking of each background image sample is completed, the intelligent terminal may classify the entire background image set according to a preset material domain, for example: the three background image samples A, B and C are included, and the corresponding material characteristics are respectively marble plate, wood plate and plastic plate, so that the three background image samples A, B and C can be respectively classified into three pattern domains of stone background, wood background and plastic background.
In this way, it is helpful to classify the background image samples in the background image set finely.
103, performing material analysis on the background image based on the pattern domain, and constructing a mapping relation between the pattern domain and the defect characteristics based on a material analysis result;
in implementation, after the intelligent terminal classifies the background image samples in the background image set, because the occurrence of part of surface defects has a strong correlation with the material, the relationship between the defect features in the defect feature set and the material features corresponding to the material domain can be established, so as to eliminate the occurrence of the condition that the defect features are matched with the background images in the unmatched material domain. Specifically, for example, the defect feature set at least includes: pit, offset, folding, scratch, damaged chip, crystal point, hole, bubble, color escape, impurity, offset, film coating, dark bubble and other types of defect characteristics, and the defect characteristics similar to the crystal point are usually only generated on a plate made of a plastic material, so that the mapping relation between the crystal point type defect characteristics and the plastic background can be established, and other conditions are similar to the crystal point type defect characteristics and are not repeated.
in implementation, the intelligent terminal may perform image fusion on the background image sample in the background image set and the defect feature in the defect feature set by generating the confrontation network image generation model based on the mapping relationship recited in step 103, specifically, the intelligent terminal performs image fusion on the background image sample as a background and the defect feature as a style feature into the background image sample.
In implementation, the mapping relationship may also
Therefore, the intelligent terminal can finally obtain the defect detection sample set generated according to the specified mapping relation.
In one embodiment, to implement image composition, step 104 may further include the following processing: generating a training sample set and a verification sample set based on the pre-acquired original plate image; and training a preset initial confrontation network generation model through the training sample set and the verification sample set to obtain the image generation model.
In this way, the intelligent terminal can be trained in advance based on the original plate images to obtain the image generation model, thereby being beneficial to improving the image synthesis efficiency.
In one embodiment, in order to optimize the generation quality of the image generation model, step 104 may further include the following processing: generating a feedback training sample set and a feedback verification sample set based on the defect detection sample set; training and updating the image generation model through the feedback training sample set and the feedback verification sample set; replacing the initial image generation model with the updated image generation model.
In this way, the intelligent terminal is helpful to continuously optimize the image generation model through a feedback mechanism so as to improve the operational capability of the image generation model.
In one embodiment, in order to expand the number of training samples, the method may further comprise the processing steps of: generating a random background image based on the material characteristics; and supplementing the random background image into the background image set, wherein the proportion of the random background image in a material domain corresponding to the background image set does not exceed a preset random threshold value.
Specifically, the random threshold may be set to 10%, 15%, 20%, or the like, and the specific value is set by a skilled person according to actual situations.
This helps to further expand the number of training samples with random background.
And 105, training and acquiring a defect detection model based on the defect detection sample set.
In implementation, after the intelligent terminal acquires the defect detection sample set, the defect detection model can be trained by using the defect detection sample set, and finally, the upgrading of the defect detection model is facilitated.
In one embodiment, the method may further comprise the processing steps of: in the training process of the defect detection model, acquiring a graded defect detection model based on the number of defect detection samples used by the defect detection model; based on the number of the used defect detection samples, the graded defect detection models are arranged in an ascending order and are connected in series to form a defect detection system; acquiring an image of a plate to be detected, inputting the image of the plate to be detected into a defect detection system, and carrying out grading detection according to the arrangement sequence of the defect detection system; and when the plate to be detected is detected to have surface defects in the image, stopping the defect detection and marking the plate to be detected as a defective product.
Therefore, the training efficiency of the defect detection model is improved while the surface defect detection effect of the plate is ensured.
Based on the same technical concept, the embodiment of the invention also provides a system for generating the surface defects of the plate based on the generation of the countermeasure network, which comprises the following components:
the system comprises an original image module, a defect feature set module and a defect feature set module, wherein the original image module is used for acquiring an original plate image and separating the original plate image into a background image set and the defect feature set;
the background classification module is used for identifying the material characteristics of each sample in the background image set and classifying the background image set into at least one material domain based on the material characteristics;
the characteristic mapping module is used for constructing a mapping relation between the material domain and the defect characteristics;
the sample synthesis module is used for synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relation through a preset image generation model;
and the detection model module is used for training and acquiring a defect detection model based on the defect detection sample set.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
the generation model training module is used for generating a training sample set and a verification sample set based on the pre-acquired original plate images; and training a preset initial confrontation network generation model through the training sample set and the verification sample set to obtain the image generation model.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
a feedback updating module for generating a feedback training sample set and a feedback verification sample set based on the defect detection sample set; training and updating the image generation model through the feedback training sample set and the feedback verification sample set; replacing the initial image generation model with the updated image generation model.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
the random background module is used for generating a random background image based on the material characteristics; and supplementing the random background image into the background image set, wherein the proportion of the random background image in a material domain corresponding to the background image set does not exceed a preset random threshold value.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
the grading detection system module is used for acquiring a grading defect detection model based on the number of defect detection samples used by the defect detection model in the training process of the defect detection model; and arranging the graded defect detection models in an ascending order based on the number of the used defect detection samples, and connecting the graded defect detection models in series to form a defect detection system.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
the grading detection module is used for acquiring an image of a plate to be detected, inputting the image of the plate to be detected into a defect detection system and carrying out grading detection according to the arrangement sequence of the defect detection system; and when the surface defect exists in the image of the plate to be detected, stopping the defect detection and marking the plate to be detected as a defective product.
In one embodiment, a system for generating surface defects of a sheet material based on generation of a countermeasure network further comprises:
the background adjusting module is used for randomly adjusting the image parameters of the background image set and the defect feature set; the random adjustment comprises a single image parameter adjustment and/or a combined adjustment of at least two image parameters.
The embodiment of the application also discloses an intelligent terminal, which comprises a memory and a processor, wherein the memory is stored with a computer program which can be loaded by the processor and can execute the method for generating the sheet surface defects based on the generation countermeasure network.
Based on the same technical concept, the embodiment of the application further discloses a computer-readable storage medium, which comprises various steps that when being loaded and executed by a processor, the method realizes the flow of the method for generating the surface defects of the sheet based on the generation countermeasure network.
The computer-readable storage medium includes, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It is obvious to those skilled in the art that, for convenience and simplicity of description, only the division of the functional modules is illustrated, and in practical applications, the above functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the above described functions.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. With this understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic disk or optical disk, etc. for storing program codes.
The above embodiments are only used to describe the technical solutions of the present application in detail, but the above embodiments are only used to help understanding the method and the core idea of the present application, and should not be construed as limiting the present application. Those skilled in the art should also appreciate that various modifications and substitutions can be easily made without departing from the scope of the present disclosure.
Claims (10)
1. A method for generating surface defects of a plate based on a generated countermeasure network is characterized by comprising the following steps: the method comprises the following steps:
acquiring an original plate image, and separating the original plate image into a background image set and a defect feature set;
identifying pattern features of each sample in the background image set, classifying the background image set into at least one pattern domain based on the pattern features;
performing material analysis on the background image based on the pattern domain, and constructing a mapping relation between the pattern domain and the defect characteristics based on the material analysis result;
synthesizing the background image set and the defect feature set into a training set and a verification set according to the mapping relation through a preset image generation model;
and training and acquiring a defect detection model based on the defect detection sample set.
2. The method for generating the surface defects of the plates based on the generation of the antagonistic network as claimed in claim 1, characterized in that: before the preset image generation model is used for synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relationship, the method further comprises the following steps:
generating a training sample set and a verification sample set based on the pre-acquired original plate images;
and training a preset initial confrontation network generation model through the training sample set and the verification sample set to obtain the image generation model.
3. The method for generating the surface defects of the plate based on the generation of the countermeasure network as claimed in claim 2, wherein: after the preset image generation model is used for synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relationship, the method further comprises the following steps:
generating a feedback training sample set and a feedback verification sample set based on the defect detection sample set;
training and updating the image generation model through the feedback training sample set and the feedback verification sample set;
replacing the initial image generation model with the updated image generation model.
4. The method for generating surface defects of a plate based on generation of a countermeasure network as claimed in claim 1, wherein the method further comprises:
generating a random background image based on the pattern features;
supplementing the random background image into the background image set, wherein the proportion of the random background image in a pattern domain corresponding to the background image set does not exceed a preset random threshold value.
5. The method for generating the surface defects of the plates based on the generation of the antagonistic network as claimed in claim 1, characterized in that: the method further comprises the following steps:
in the training process of the defect detection model, acquiring a graded defect detection model based on the number of defect detection samples used by the defect detection model;
and arranging the graded defect detection models in an ascending order based on the number of the used defect detection samples, and connecting the graded defect detection models in series to form a defect detection system.
6. The method for generating the surface defects of the plate based on the generation of the antagonistic network as claimed in claim 5, wherein: the step of arranging the graded defect detection models in an ascending order based on the number of the used defect detection samples, and connecting the graded defect detection models in series to form a defect detection system, further comprises:
acquiring an image of a plate to be detected, inputting the image of the plate to be detected into a defect detection system, and carrying out grading detection according to the arrangement sequence of the defect detection system;
and when the surface defect exists in the image of the plate to be detected, stopping the defect detection and marking the plate to be detected as a defective product.
7. The method for generating the surface defects of the plate based on the generation of the antagonistic network as claimed in claim 1, wherein: after the obtaining of the original plate image and the separating of the original plate image into the background image set and the defect feature set, the method further includes:
randomly adjusting the image parameters of the background image set and the defect feature set;
the random adjustment comprises a single image parameter adjustment and/or a combined adjustment of at least two image parameters.
8. A plate surface defect generation system based on generation of a countermeasure network is characterized in that: the system comprises:
the system comprises an original image module, a defect feature set module and a defect feature set module, wherein the original image module is used for acquiring an original plate image and separating the original plate image into a background image set and the defect feature set;
a background classification module for identifying pattern features of each sample in the background image set, classifying the background image set into at least one pattern domain based on the pattern features;
the characteristic mapping module is used for performing material analysis on the background image based on the pattern domain and constructing a mapping relation between the pattern domain and the defect characteristics based on a material analysis result;
the sample synthesis module is used for synthesizing the background image set and the defect feature set into a defect detection sample set according to the mapping relation through a preset image generation model;
and the detection model module is used for training and acquiring a defect detection model based on the defect detection sample set.
9. An intelligent terminal, characterized in that the intelligent terminal comprises a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the method for generating the surface defects of the plate based on the generation countermeasure network according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the storage medium, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by a processor to implement the method for generating surface defects of a sheet material based on a generated countermeasure network according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859013.9A CN115240031B (en) | 2022-07-21 | 2022-07-21 | Board surface defect generation method and system based on generation countermeasure network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859013.9A CN115240031B (en) | 2022-07-21 | 2022-07-21 | Board surface defect generation method and system based on generation countermeasure network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115240031A true CN115240031A (en) | 2022-10-25 |
| CN115240031B CN115240031B (en) | 2023-10-27 |
Family
ID=83674186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210859013.9A Active CN115240031B (en) | 2022-07-21 | 2022-07-21 | Board surface defect generation method and system based on generation countermeasure network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240031B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937595A (en) * | 2022-12-20 | 2023-04-07 | 中交公路长大桥建设国家工程研究中心有限公司 | Bridge apparent anomaly identification method and system based on intelligent data processing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108447054A (en) * | 2018-03-22 | 2018-08-24 | 北京木业邦科技有限公司 | Defects in timber sample acquiring method, device, electronic equipment and storage medium |
| CN109829483A (en) * | 2019-01-07 | 2019-05-31 | 鲁班嫡系机器人（深圳）有限公司 | Defect recognition model training method, device, computer equipment and storage medium |
| CN110570316A (en) * | 2018-08-31 | 2019-12-13 | 阿里巴巴集团控股有限公司 | method and device for training damage recognition model |
| CN111311544A (en) * | 2020-01-19 | 2020-06-19 | 无锡赛默斐视科技有限公司 | Floor defect detection method based on deep learning |
| CN112017182A (en) * | 2020-10-22 | 2020-12-01 | 北京中鼎高科自动化技术有限公司 | Industrial-grade intelligent surface defect detection method |
| CN113205176A (en) * | 2021-04-19 | 2021-08-03 | 重庆创通联达智能技术有限公司 | Method, device and equipment for training defect classification detection model and storage medium |
| CN113283541A (en) * | 2021-06-15 | 2021-08-20 | 无锡锤头鲨智能科技有限公司 | Automatic floor sorting method |
| US20210374928A1 (en) * | 2020-05-26 | 2021-12-02 | Fujitsu Limited | Defect detection method and apparatus |
| CN114387230A (en) * | 2021-12-28 | 2022-04-22 | 北京科技大学 | PCB defect detection method based on re-verification detection |
-
2022
- 2022-07-21 CN CN202210859013.9A patent/CN115240031B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108447054A (en) * | 2018-03-22 | 2018-08-24 | 北京木业邦科技有限公司 | Defects in timber sample acquiring method, device, electronic equipment and storage medium |
| CN110570316A (en) * | 2018-08-31 | 2019-12-13 | 阿里巴巴集团控股有限公司 | method and device for training damage recognition model |
| US20200090320A1 (en) * | 2018-08-31 | 2020-03-19 | Alibaba Group Holding Limited | System and method for training a damage identification model |
| CN109829483A (en) * | 2019-01-07 | 2019-05-31 | 鲁班嫡系机器人（深圳）有限公司 | Defect recognition model training method, device, computer equipment and storage medium |
| CN111311544A (en) * | 2020-01-19 | 2020-06-19 | 无锡赛默斐视科技有限公司 | Floor defect detection method based on deep learning |
| US20210374928A1 (en) * | 2020-05-26 | 2021-12-02 | Fujitsu Limited | Defect detection method and apparatus |
| CN114092386A (en) * | 2020-05-26 | 2022-02-25 | 富士通株式会社 | Defect detection method and apparatus |
| CN112017182A (en) * | 2020-10-22 | 2020-12-01 | 北京中鼎高科自动化技术有限公司 | Industrial-grade intelligent surface defect detection method |
| CN113205176A (en) * | 2021-04-19 | 2021-08-03 | 重庆创通联达智能技术有限公司 | Method, device and equipment for training defect classification detection model and storage medium |
| CN113283541A (en) * | 2021-06-15 | 2021-08-20 | 无锡锤头鲨智能科技有限公司 | Automatic floor sorting method |
| CN114387230A (en) * | 2021-12-28 | 2022-04-22 | 北京科技大学 | PCB defect detection method based on re-verification detection |
Non-Patent Citations (1)
| Title |
|---|
| 尹奎龙等: "工业CT/DR检测系统在盆式绝缘子检测中的应用研究", 山东电力技术, no. 08 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937595A (en) * | 2022-12-20 | 2023-04-07 | 中交公路长大桥建设国家工程研究中心有限公司 | Bridge apparent anomaly identification method and system based on intelligent data processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115240031B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179251B (en) | Defect detection system and method based on twin neural network and by utilizing template comparison | |
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| WO2019117065A1 (en) | Data generation device, data generation method and data generation program | |
| US20190118226A1 (en) | Sorting system | |
| CN107403424A (en) | A kind of car damage identification method based on image, device and electronic equipment | |
| CN109919934A (en) | A kind of liquid crystal display panel defect inspection method based on the study of multi-source domain depth migration | |
| CN114494780A (en) | Semi-supervised industrial defect detection method and system based on feature comparison | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| CN108682003B (en) | Product quality detection method | |
| CN112070137B (en) | Training data set generation method, target object detection method and related equipment | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| CN111079815B (en) | Automatic high-value electronic device identification method for disassembly of waste circuit board | |
| JP2016191589A (en) | Defect classification device defect classification method | |
| CN110659371B (en) | Automatic batch generation method and device for banner images of target objects | |
| CN111754502A (en) | Method for detecting surface defects of magnetic core based on fast-RCNN algorithm of multi-scale feature fusion | |
| Schwebig et al. | Compilation of training datasets for use of convolutional neural networks supporting automatic inspection processes in industry 4.0 based electronic manufacturing | |
| CN113222913A (en) | Circuit board defect detection positioning method and device and storage medium | |
| CN114359235A (en) | Wood surface defect detection method based on improved YOLOv5l network | |
| CN115240031A (en) | Method and system for generating plate surface defects based on generation countermeasure network | |
| CN110705400A (en) | Method for automatically splitting examination paper layout questions | |
| CN116563230A (en) | Weld defect identification method and system | |
| CN111105399A (en) | Switch surface defect detection method and system | |
| CN114863125A (en) | Intelligent scoring method and system for calligraphy/fine art works | |
| Ruediger-Flore et al. | CAD-based data augmentation and transfer learning empowers part classification in manufacturing | |
| CN117473409A (en) | PCB panel defect classification method, system, equipment and storage medium |
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 |