模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (8): 692-702    DOI: 10.16451/j.cnki.issn1003-6059.202408003
Detection and Recognition Algorithms in Realistic Scene Current Issue| Next Issue| Archive| Adv Search |
Lightweight Steel Surface Defect Detection Algorithm Based on Improved RetinaNet
WANG Weijia1, ZHANG Yu2, WANG Jinghua1, XU Yong1
1. School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518055;
2. Intelligent Equipment Division, HBIS Digital Technology Co., Ltd., Shijiazhuang 053099

Download: PDF (1626 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  For the requirement of the practical application, the existing defect detection algorithms suffer from the problems of slow detection speed and low detection accuracy. To address these issues, a lightweight steel surface defect detection algorithm based on improved RetinaNet is proposed. Firstly, the original backbone network is replaced by a lightweight network, and a cross-stage-partial structure is introduced to achieve effective propagation and lightweighting of gradients. Then, depth-separable convolution is employed to replace the traditional convolutional layer to further reduce the number of parameters and improve the detection speed. To compensate for the decrease in model accuracy caused by lightweighting, a spatial pyramid pooling mechanism based on the cross-stage partial structure is designed. The detection accuracy of the model is effectively improved by feature fusion at different scales. Finally, experiments on NEU-DET dataset and the self-built HBIS dataset demonstrate the proposed algorithm reaches a faster detection speed and higher accuracy. Moreover, the corresponding hardware and software system meets the real-time online detection requirements of the production line and it has been put into service.
Key wordsLightweight Modeling      Object Detection      Cross-Stage Partial Structure      Steel Surface Defect Detection     
Received: 29 February 2024     
ZTFLH: TP391  
Corresponding Authors: XU Yong, Ph.D., professor. His research interests include pa-ttern recognition and deep learning.   
About author:: WANG Weijia, Master student. His research interests include computer vision and object detection. ZHANG Yu, Bachelor. His research interests include computer vision and defect detection. WANG Jinghua, Ph.D., associate profe-ssor. His research interests include computer vision and unsupervised learning.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
WANG Weijia
ZHANG Yu
WANG Jinghua
XU Yong
Cite this article:   
WANG Weijia,ZHANG Yu,WANG Jinghua等. Lightweight Steel Surface Defect Detection Algorithm Based on Improved RetinaNet[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(8): 692-702.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202408003      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I8/692
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn