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
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.
[1] TABERNIK D, ŠELA S, SKVARČ J, et al. Segmentation-Based Deep-Learning Approach for Surface-Defect Detection. Journal of Intelligent Manufacturing, 2020, 31(3): 759-776. [2] CHEN Y J, DING Y Y, ZHAO F, et al. Surface Defect Detection Methods for Industrial Products: A Review. Applied Sciences, 2021, 11(16). DOI: 10.3390/app11167657. [3] 郭渊,周俊.基于机器视觉的轴承缺陷检测研究进展.机电工程, 2024, 41(5): 761-774. (GUO Y, ZHOU J.Research Progress of Bearing Defect Detection Based on Machine Vision. Journal of Mechanical and Electrical Engineering, 2024, 41(5): 761-774.) [4] RAVIKUMAR S, RAMACHANDRAN K I, SUGUMARAN V.Machine Learning Approach for Automated Visual Inspection of Machine Components. Expert Systems with Applications, 2011, 38(4): 3260-3266. [5] TOLBA A S, RAAFAT H M.Multiscale Image Quality Measures for Defect Detection in Thin Films. The International Journal of Advanced Manufacturing Technology, 2015, 79: 113-122. [6] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 580-587. [7] GIRSHICK R.Fast R-CNN // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 1140-1148. [8] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. [9] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once: Unified, Realtime Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 779-788. [10] REDMON J, FARHADI A.YOLO9000: Better, Faster, Stronger // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 6517-6525. [11] REDMON J, FARHADI A.YOLOv3: An Incremental Improvement[C/OL]. [2024-01-15].https://arxiv.org/pdf/1804.02767v1. [12] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[C/OL].[2024-01-15]. https://arxiv.org/pdf/2004.10934. [13] LI C, LI L, JIANG H, et al. YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications[C/OL].[2024-01-15].https://arxiv.org/pdf/2209.02976. [14] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: Trai-nable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 7464-7475. [15] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multi-box Detector // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37. [16] WANG W Y, MI C F, WU Z H, et al. A Real-Time Steel Surface Defect Detection Approach with High Accuracy. IEEE Transactions on Instrumentation and Measurement, 2022, 71. DOI: 10.1109/TIM.2021.3127648. [17] 李若尘,朱悠翔,孙卫民,等.基于深度学习的木材缺陷图像的识别与定位.数据采集与处理, 2020, 35(3): 494-505. (LI R C, ZHU Y X, SUN W M, et al. Recognition and Localization of Wood Defect Image Based on Deep Learning. Journal of Data Acquisition and Processing, 2020, 35(3): 494-505.) [18] 黄健,郑春厚,章军,等.基于小样本度量迁移学习的表面缺陷检测.模式识别与人工智能, 2021, 34(5): 407-414. (HUANG J,ZHENG C H,ZHANG J, et al. Few-Shot Metric Transfer Learning Network for Surface Defect Detection. Pattern Recognition and Artificial Intelligence, 2021, 34(5): 407-414.) [19] 张兰尧,陈晓玲,张达敏,等.ValidFlow:基于标准化流的无监督图像缺陷检测.数据采集与处理, 2023,38(6): 1445-1457. (ZHANG L Y, CHEN X L, ZHANG D M, et al. ValidFlow: Unsupervised Image Defect Detection Based on Normalizing Flows. Journal of Data Acquisition and Processing, 2023, 38(6): 1445-1457.) [20] 王宪保,刘鹏飞,项圣,等. 基于神经架构搜索的非结构化剪枝方法.模式识别与人工智能, 2023, 36(5): 448-458. (WANG X B, LIU P F, XIANG S, et al. Unstructured Pruning Method Based on Neural Architecture Search. Pattern Recognition and Artificial Intelligence, 2023, 36(5): 448-458.) [21] LI L L, WANG Z F, ZHANG T T.GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection. Electronics, 2023, 12(3). DOI: 10.3390/electronics12030561. [22] HAN K, WANG Y H, TIAN Q, et al. GhostNet: More Features from Cheap Operations // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 1577-1586. [23] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 2999-3007. [24] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [25] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 936-944. [26] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: A New Backbone That Can Enhance Learning Capability of CNN // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition Workshops. Washington, USA: IEEE, 2020: 1571-1580. [27] HOWARD A G, ZHU M L, CHEN B, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[C/OL].[2024-01-15]. https://arxiv.org/pdf/1704.04861v1. [28] HE K M, ZHANG X Y, REN S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Tran-sactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. [29] HE Y, SONG K C, MENG Q G, et al. An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features. IEEE Transactions on Instrumentation and Measurement, 2019, 69(4): 1493-1504.
2024, Vol. 37 
