Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products

Owing to the remarkable development of deep learning algorithms, defect detection techniques based on deep neural networks have been extensively applied in industrial production. Most existing surface defect detection models assign equal costs to the classification errors among different defect cate...

Full description

Bibliographic Details
Main Authors: Ben Liu, Feng Gao, Yan Li
Format: Article
Language:English
Published: MDPI AG 2023-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/5/2610
_version_ 1797614402303688704
author Ben Liu
Feng Gao
Yan Li
author_facet Ben Liu
Feng Gao
Yan Li
author_sort Ben Liu
collection DOAJ
description Owing to the remarkable development of deep learning algorithms, defect detection techniques based on deep neural networks have been extensively applied in industrial production. Most existing surface defect detection models assign equal costs to the classification errors among different defect categories but do not strictly distinguish them. However, various errors can generate a great discrepancy in decision risk or classification costs and then produce a cost-sensitive issue that is crucial to the manufacturing process. To address this engineering challenge, we propose a novel supervised classification cost-sensitive learning method (SCCS) and apply it to improve YOLOv5 as CS-YOLOv5, where the classification loss function of object detection was reconstructed according to a new cost-sensitive learning criterion explained by a label–cost vector selection method. In this way, the classification risk information from a cost matrix is directly introduced into the detection model and fully exploited in training. As a result, the developed approach can make low-risk classification decisions for defect detection. It is applicable for direct cost-sensitive learning based on a cost matrix to implement detection tasks. Using two datasets of a painting surface and a hot-rolled steel strip surface, our CS-YOLOv5 model outperforms the original version with respect to cost under different positive classes, coefficients, and weight ratios, but also maintains effective detection performance measured by mAP and F1 scores.
first_indexed 2024-03-11T07:10:53Z
format Article
id doaj.art-d9c8982d5c0841bdb90c9f1a14fb9f17
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-11T07:10:53Z
publishDate 2023-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-d9c8982d5c0841bdb90c9f1a14fb9f172023-11-17T08:37:12ZengMDPI AGSensors1424-82202023-02-01235261010.3390/s23052610Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial ProductsBen Liu0Feng Gao1Yan Li2School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaOwing to the remarkable development of deep learning algorithms, defect detection techniques based on deep neural networks have been extensively applied in industrial production. Most existing surface defect detection models assign equal costs to the classification errors among different defect categories but do not strictly distinguish them. However, various errors can generate a great discrepancy in decision risk or classification costs and then produce a cost-sensitive issue that is crucial to the manufacturing process. To address this engineering challenge, we propose a novel supervised classification cost-sensitive learning method (SCCS) and apply it to improve YOLOv5 as CS-YOLOv5, where the classification loss function of object detection was reconstructed according to a new cost-sensitive learning criterion explained by a label–cost vector selection method. In this way, the classification risk information from a cost matrix is directly introduced into the detection model and fully exploited in training. As a result, the developed approach can make low-risk classification decisions for defect detection. It is applicable for direct cost-sensitive learning based on a cost matrix to implement detection tasks. Using two datasets of a painting surface and a hot-rolled steel strip surface, our CS-YOLOv5 model outperforms the original version with respect to cost under different positive classes, coefficients, and weight ratios, but also maintains effective detection performance measured by mAP and F1 scores.https://www.mdpi.com/1424-8220/23/5/2610defect detectioncost-sensitive learningYOLOv5misclassification riskintelligent industry
spellingShingle Ben Liu
Feng Gao
Yan Li
Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
Sensors
defect detection
cost-sensitive learning
YOLOv5
misclassification risk
intelligent industry
title Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
title_full Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
title_fullStr Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
title_full_unstemmed Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
title_short Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products
title_sort cost sensitive yolov5 for detecting surface defects of industrial products
topic defect detection
cost-sensitive learning
YOLOv5
misclassification risk
intelligent industry
url https://www.mdpi.com/1424-8220/23/5/2610
work_keys_str_mv AT benliu costsensitiveyolov5fordetectingsurfacedefectsofindustrialproducts
AT fenggao costsensitiveyolov5fordetectingsurfacedefectsofindustrialproducts
AT yanli costsensitiveyolov5fordetectingsurfacedefectsofindustrialproducts