A Four-Stage Product Appearance Defect Detection Method With Small Samples
With the automation of industrial production, appearance defect detection based on machine vision plays an important role in product quality control. The scarcity of defect samples and real-time requirement are the main challenges in this field. Many existing studies are based on semantic segmentati...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9851632/ |
| _version_ | 1798039938863726592 |
|---|---|
| author | Xiang Xie Rongfeng Zhang Lingxi Peng Shaohu Peng |
| author_facet | Xiang Xie Rongfeng Zhang Lingxi Peng Shaohu Peng |
| author_sort | Xiang Xie |
| collection | DOAJ |
| description | With the automation of industrial production, appearance defect detection based on machine vision plays an important role in product quality control. The scarcity of defect samples and real-time requirement are the main challenges in this field. Many existing studies are based on semantic segmentation network, but they cannot provide a classification confidence score for each image and only report the segmentation tasks metrics, which ignore that the positive or negative decisions are the key of defect detection. Therefore, this paper proposes a four-stage appearance defect detection model: contrast enhancement, segmentation, correction, and decision, which can achieve high detection accuracy with a severe shortage of positive samples. Since the proposed model simplifies U-Net to segment those candidate defect regions, and constructs a lightweight decision network based on the candidate regions and segmented mask, the proposed method not only achieves fast inference speed, but also obtain good performance with fewer defect samples. Experiments are implemented on three public datasets: magnetic tile dataset, Kolektor surface defect dataset and DAGM2007 dataset. The influence of each module on the detection accuracy is analyzed. Experimental results show that the proposed model achieves excellent performance comparing with other state-of-art methods. |
| first_indexed | 2024-04-11T22:00:36Z |
| format | Article |
| id | doaj.art-ab412b5e4853439fab03d82553ac0a77 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T22:00:36Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ab412b5e4853439fab03d82553ac0a772022-12-22T04:00:57ZengIEEEIEEE Access2169-35362022-01-0110837408375410.1109/ACCESS.2022.31969359851632A Four-Stage Product Appearance Defect Detection Method With Small SamplesXiang Xie0https://orcid.org/0000-0002-4277-574XRongfeng Zhang1Lingxi Peng2Shaohu Peng3School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou, ChinaWith the automation of industrial production, appearance defect detection based on machine vision plays an important role in product quality control. The scarcity of defect samples and real-time requirement are the main challenges in this field. Many existing studies are based on semantic segmentation network, but they cannot provide a classification confidence score for each image and only report the segmentation tasks metrics, which ignore that the positive or negative decisions are the key of defect detection. Therefore, this paper proposes a four-stage appearance defect detection model: contrast enhancement, segmentation, correction, and decision, which can achieve high detection accuracy with a severe shortage of positive samples. Since the proposed model simplifies U-Net to segment those candidate defect regions, and constructs a lightweight decision network based on the candidate regions and segmented mask, the proposed method not only achieves fast inference speed, but also obtain good performance with fewer defect samples. Experiments are implemented on three public datasets: magnetic tile dataset, Kolektor surface defect dataset and DAGM2007 dataset. The influence of each module on the detection accuracy is analyzed. Experimental results show that the proposed model achieves excellent performance comparing with other state-of-art methods.https://ieeexplore.ieee.org/document/9851632/Appearance defect detectionconvolutional neural networksemantic segmentationsmall defect samples |
| spellingShingle | Xiang Xie Rongfeng Zhang Lingxi Peng Shaohu Peng A Four-Stage Product Appearance Defect Detection Method With Small Samples IEEE Access Appearance defect detection convolutional neural network semantic segmentation small defect samples |
| title | A Four-Stage Product Appearance Defect Detection Method With Small Samples |
| title_full | A Four-Stage Product Appearance Defect Detection Method With Small Samples |
| title_fullStr | A Four-Stage Product Appearance Defect Detection Method With Small Samples |
| title_full_unstemmed | A Four-Stage Product Appearance Defect Detection Method With Small Samples |
| title_short | A Four-Stage Product Appearance Defect Detection Method With Small Samples |
| title_sort | four stage product appearance defect detection method with small samples |
| topic | Appearance defect detection convolutional neural network semantic segmentation small defect samples |
| url | https://ieeexplore.ieee.org/document/9851632/ |
| work_keys_str_mv | AT xiangxie afourstageproductappearancedefectdetectionmethodwithsmallsamples AT rongfengzhang afourstageproductappearancedefectdetectionmethodwithsmallsamples AT lingxipeng afourstageproductappearancedefectdetectionmethodwithsmallsamples AT shaohupeng afourstageproductappearancedefectdetectionmethodwithsmallsamples AT xiangxie fourstageproductappearancedefectdetectionmethodwithsmallsamples AT rongfengzhang fourstageproductappearancedefectdetectionmethodwithsmallsamples AT lingxipeng fourstageproductappearancedefectdetectionmethodwithsmallsamples AT shaohupeng fourstageproductappearancedefectdetectionmethodwithsmallsamples |