WO2023236372A1 - Procédé de détection de défaut de surface, basé sur une reconnaissance d'image - Google Patents
Procédé de détection de défaut de surface, basé sur une reconnaissance d'image Download PDFInfo
- Publication number
- WO2023236372A1 WO2023236372A1 PCT/CN2022/116053 CN2022116053W WO2023236372A1 WO 2023236372 A1 WO2023236372 A1 WO 2023236372A1 CN 2022116053 W CN2022116053 W CN 2022116053W WO 2023236372 A1 WO2023236372 A1 WO 2023236372A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- picture
- image data
- neural network
- network model
- image
- Prior art date
Links
- 230000007547 defect Effects 0.000 title claims abstract description 78
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000003062 neural network model Methods 0.000 claims abstract description 83
- 238000007781 pre-processing Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000010008 shearing Methods 0.000 claims description 10
- 238000009776 industrial production Methods 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V10/54—Extraction of image or video features relating to texture
-
- 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
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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
Definitions
- the purpose of the present invention is to provide a surface defect detection method based on picture recognition, which preprocesses the collected picture data and converts it into a number of associated picture data to form a picture data set; and uses the picture data set to perform the first preprocessing Assume that the neural network model and the second preset neural network model are trained, and the target picture is recognized and analyzed through the two neural network models to determine the object status information contained in the target picture and the surface structure defect status information of the object present in the target picture.
- the above surface defect detection method preprocesses the collected picture data and converts it into associated picture data, which can fully enrich the types of picture data in the picture data collection and realize the neural network Comprehensive and effective training of the model enables the above method to be applied to pictures obtained under different shooting conditions, effectively extended to different picture recognition situations, and improves the accuracy and reliability of object surface defect detection.
- Step S2 Use the picture data set to train the first preset neural network model; input the target picture into the first preset neural network model for recognition and analysis to determine the object state information contained in the target picture;
- Step S3 Determine whether the target picture is a valid picture according to the object status information contained in the frame of the target picture; and use the picture data set to train the second preset neural network model;
- Step S4 Input the target picture judged to be a valid picture into the second preset neural network model for identification and analysis to determine the surface structure defect status information of the object present in the target picture; and then according to the surface structure defect status information to mark the target image.
- step S1 collecting a predetermined amount of picture data, preprocessing each picture data, thereby converting each picture data into several associated picture data specifically includes:
- At least one of flipping preprocessing, scaling preprocessing and shearing preprocessing is performed on each image data, thereby converting each image data into several associated image data.
- step S1 flipping preprocessing on each picture data specifically includes:
- the image is rotated at several random angles, thereby converting the image data into several associated image data;
- step S1 scaling preprocessing of each image data specifically includes:
- the image corresponding to the image data is scaled by several random scaling factors, thereby converting the image data into several associated image data;
- the shearing preprocessing of each picture data specifically includes:
- a number of random amplitude shearing processes are performed along different boundaries of the image corresponding to the image data, thereby converting the image data into a number of associated image data.
- step S1 forming a picture data set from a number of associated picture data corresponding to all picture data specifically includes:
- All associated image data corresponding to each image data are randomly arranged and combined to form a corresponding image data set.
- step S2 using the picture data set to train the first preset neural network model specifically includes:
- the training of the first preset neural network model is completed; otherwise, a predetermined number of associated picture data is randomly selected from the picture data set to train the first preset neural network model.
- the neural network model is trained again until the model convergence degree meets predetermined convergence conditions.
- step S2 the target picture is input into the first preset neural network model for recognition and analysis, and it is determined that the object state information contained in the frame of the target picture specifically includes:
- the target picture is input into the first preset neural network model that has completed training for recognition and analysis, and the type of object contained in the picture of the target picture and the total pixel area of the corresponding object in the picture are determined.
- step S3 judging whether the target picture is a valid picture according to the object status information contained in the frame of the target picture specifically includes:
- step S3 using the picture data set to train the second preset neural network model specifically includes:
- the target picture judged to be a valid picture is input into the second preset neural network model for identification and analysis, and the location coordinates of the surface defect of the object present in the target picture and the shape and size of the surface defect are determined.
- marking the target image according to the surface structure defect status information specifically includes:
- an embodiment means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application.
- the appearances of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those skilled in the art understand, both explicitly and implicitly, that the embodiments described herein may be combined with other embodiments.
- An embodiment of the present application provides a surface defect detection method based on image recognition.
- the surface defect detection method based on image recognition includes the following steps:
- Step S1 collect a predetermined amount of picture data, preprocess each picture data, thereby converting each picture data into a number of associated picture data; then form a picture data set by forming a number of associated picture data corresponding to all the picture data;
- the above-mentioned surface defect detection method preprocesses the collected picture data and converts it into a number of related picture data to form a picture data set; and uses the picture data set to train the first preset neural network model and the second preset neural network model. , identify and analyze the target picture through two neural network models, determine the object status information contained in the target picture and the surface structure defect status information of the objects present in the target picture, and then conduct the target picture based on the surface structure defect status information.
- the above surface defect detection method preprocesses the collected image data and converts it into associated image data, which can fully enrich the types of image data in the image data collection and achieve comprehensive and effective training of the neural network model, making the above method applicable to different The pictures obtained under the shooting conditions can be effectively extended to different picture recognition situations to improve the accuracy and reliability of object surface defect detection.
- step S1 a predetermined amount of picture data is collected, and each picture data is preprocessed, thereby converting each picture data into several associated picture data, specifically including:
- At least one of flipping preprocessing, scaling preprocessing and shearing preprocessing is performed on each image data, thereby converting each image data into several associated image data.
- each image data is separately subjected to flipping preprocessing, scaling preprocessing and shearing preprocessing, so that each image data can derive multiple associated image data respectively, thereby maximizing Enrich the type and content of image data to the maximum extent to ensure comprehensive and reliable subsequent training of neural network models.
- step S1 performing flip preprocessing on each image data specifically includes:
- the image is rotated at several random angles, thereby converting the image data into several associated image data;
- step S1 scaling preprocessing of each image data specifically includes:
- the image corresponding to the image data is scaled by several random scaling factors, thereby converting the image data into several associated image data;
- a number of random amplitude shearing processes are performed along different boundaries of the image corresponding to the image data, thereby converting the image data into a number of associated image data.
- the image corresponding to the image data is flipped, scaled, and cut, so that the same image data can be converted into multiple associated image data in different content forms through simple image processing operations, thereby improving the conversion of associated image data.
- step S1 forming a picture data set from several associated picture data corresponding to all picture data specifically includes:
- All associated image data corresponding to each image data are randomly arranged and combined to form a corresponding image data set.
- step S2 using the picture data set to train the first preset neural network model specifically includes:
- the target picture is input into the first preset neural network model that has completed training for recognition and analysis, and the type of object contained in the picture of the target picture and the total pixel area of the corresponding object in the picture are determined.
- the first preset neural network model can perform outline and texture recognition of objects that always exist in the target picture, thereby determining the types of objects contained in the target picture and the total pixel area of the corresponding objects in the picture, and realizing All objects present in the target picture are comprehensively and accurately recognized and detected.
- the object type determine whether the target picture contains a predetermined type of object; if not, determine that the target picture does not belong to a valid picture;
- the training of the second preset neural network model is completed; otherwise, a predetermined number of associated image data is randomly selected from the image data set to train the second preset neural network model again. Training is performed until the model convergence degree meets predetermined convergence conditions.
- the second preset neural network model is trained at least once using the picture data set as the training data source, so that the second preset neural network model can reliably identify and detect objects in the target picture.
- the second preset neural network model can be but is not limited to YOLO v5 model.
- the pixel sharpening process is performed on the picture area corresponding to the surface defect, and the position coordinates of the surface defect and the shape and size related information of the surface defect are added to the picture area corresponding to the surface defect.
Abstract
Un procédé de détection de défaut de surface, basé sur une reconnaissance d'image, est caractérisé par : le prétraitement de données d'image collectées à convertir en une pluralité d'éléments de données d'image associées de façon à former un ensemble de données d'image ; l'apprentissage d'un premier modèle de réseau neuronal prédéfini et d'un second modèle de réseau neuronal prédéfini à l'aide de l'ensemble de données d'image, la reconnaissance et l'analyse d'une image cible au moyen des deux modèles de réseau neuronal pour déterminer des informations d'état d'objet comprises dans une représentation de l'image cible et des informations d'état de défaut de structure de surface d'un objet existant dans l'image cible, et le marquage de l'image cible selon les informations d'état de défaut de structure de surface. Selon le procédé de détection de défaut de surface, les données d'image collectées sont prétraitées pour être converties en des données d'image associées de sorte que le type des données d'image dans l'ensemble de données d'image peut être intégralement enrichi, et un apprentissage complet et efficace des modèles de réseau neuronal est mis en œuvre. Le procédé peut être approprié pour des images obtenues dans différentes conditions photographiques de sorte que la précision et la fiabilité de détection de défaut de surface d'un objet sont améliorées.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210649891.8 | 2022-06-09 | ||
CN202210649891.8A CN114882010A (zh) | 2022-06-09 | 2022-06-09 | 基于图片识别的表面缺陷检测方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023236372A1 true WO2023236372A1 (fr) | 2023-12-14 |
Family
ID=82682521
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/116053 WO2023236372A1 (fr) | 2022-06-09 | 2022-08-31 | Procédé de détection de défaut de surface, basé sur une reconnaissance d'image |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114882010A (fr) |
WO (1) | WO2023236372A1 (fr) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114882010A (zh) * | 2022-06-09 | 2022-08-09 | 苏州大学 | 基于图片识别的表面缺陷检测方法 |
CN115165920B (zh) * | 2022-09-06 | 2023-06-16 | 南昌昂坤半导体设备有限公司 | 一种三维缺陷检测方法及检测设备 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067020A (zh) * | 2016-06-02 | 2016-11-02 | 广东工业大学 | 实时场景下快速获取有效图像的系统和方法 |
CN108022235A (zh) * | 2017-11-23 | 2018-05-11 | 中国科学院自动化研究所 | 高压输电铁塔关键部件缺陷识别方法 |
CN108647648A (zh) * | 2018-05-14 | 2018-10-12 | 电子科技大学 | 一种基于卷积神经网络的可见光条件下的舰船识别系统及方法 |
CN111681215A (zh) * | 2020-05-29 | 2020-09-18 | 无锡赛睿科技有限公司 | 卷积神经网络模型训练方法、加工件缺陷检测方法及装置 |
WO2021143343A1 (fr) * | 2020-01-15 | 2021-07-22 | 歌尔股份有限公司 | Procédé et dispositif de test de qualité de produit |
CN114882010A (zh) * | 2022-06-09 | 2022-08-09 | 苏州大学 | 基于图片识别的表面缺陷检测方法 |
-
2022
- 2022-06-09 CN CN202210649891.8A patent/CN114882010A/zh active Pending
- 2022-08-31 WO PCT/CN2022/116053 patent/WO2023236372A1/fr unknown
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067020A (zh) * | 2016-06-02 | 2016-11-02 | 广东工业大学 | 实时场景下快速获取有效图像的系统和方法 |
CN108022235A (zh) * | 2017-11-23 | 2018-05-11 | 中国科学院自动化研究所 | 高压输电铁塔关键部件缺陷识别方法 |
CN108647648A (zh) * | 2018-05-14 | 2018-10-12 | 电子科技大学 | 一种基于卷积神经网络的可见光条件下的舰船识别系统及方法 |
WO2021143343A1 (fr) * | 2020-01-15 | 2021-07-22 | 歌尔股份有限公司 | Procédé et dispositif de test de qualité de produit |
CN111681215A (zh) * | 2020-05-29 | 2020-09-18 | 无锡赛睿科技有限公司 | 卷积神经网络模型训练方法、加工件缺陷检测方法及装置 |
CN114882010A (zh) * | 2022-06-09 | 2022-08-09 | 苏州大学 | 基于图片识别的表面缺陷检测方法 |
Also Published As
Publication number | Publication date |
---|---|
CN114882010A (zh) | 2022-08-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023236372A1 (fr) | Procédé de détection de défaut de surface, basé sur une reconnaissance d'image | |
US11922615B2 (en) | Information processing device, information processing method, and storage medium | |
US8351662B2 (en) | System and method for face verification using video sequence | |
CN104636706B (zh) | 一种基于梯度方向一致性复杂背景条码图像自动分割方法 | |
CN109711407B (zh) | 一种车牌识别的方法及相关装置 | |
CN108985170A (zh) | 基于三帧差分法及深度学习的输电线路悬挂物识别方法 | |
CN110096945B (zh) | 基于机器学习的室内监控视频关键帧实时提取方法 | |
CN109740572A (zh) | 一种基于局部彩色纹理特征的人脸活体检测方法 | |
WO2014036813A1 (fr) | Procédé et dispositif d'extraction de traits caractéristiques d'images | |
WO2020249054A1 (fr) | Procédé et système de détection de corps vivant d'un visage humain à l'aide de deux caméras à longue ligne de base | |
CN106548131A (zh) | 一种基于行人检测的施工人员安全帽实时检测方法 | |
WO2023236371A1 (fr) | Procédé d'analyse visuelle pour identification d'éléments de câble | |
CN111259891A (zh) | 一种自然场景下身份证识别方法、装置、设备和介质 | |
CN113743378B (zh) | 一种基于视频的火情监测方法和装置 | |
CN115861210A (zh) | 一种基于孪生网络的变电站设备异常检测方法和系统 | |
TWI620148B (zh) | 監控裝置、監控方法及計數方法 | |
CN103544692A (zh) | 基于统计学判断的双重压缩jpeg图象篡改盲检测方法 | |
CN114821274A (zh) | 一种用于识别分合指示牌的状态的方法和设备 | |
CN110728214B (zh) | 一种基于尺度匹配的弱小人物目标检测方法 | |
CN111597939A (zh) | 一种基于深度学习的高铁线路鸟窝缺陷检测方法 | |
CN108334823A (zh) | 基于机器学习的高分辨率遥感影像集装箱区域检测方法 | |
CN112686285B (zh) | 一种基于计算机视觉的工程质量检测方法及系统 | |
CN111209863B (zh) | 一种活体模型训练和人脸活体检测方法、装置和电子设备 | |
CN112907553A (zh) | 一种基于Yolov3的高清图像目标检测方法 | |
CN108133210B (zh) | 一种图像格式识别方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22945506 Country of ref document: EP Kind code of ref document: A1 |