I. J. of Electrical & Electronics Research
Research Article | 
Research on Steel Surface Defect Detection Algorithm Based on Improved Deep Learning
Author(s): Fei Ren1, GuangRong Wang2, ZhiQi Hu3, MinNing Wu4 and Madhavi Devaraj5
Published In : International Journal of Electrical and Electronics Research (IJEER) Volume 10, Issue 4
Publisher : FOREX Publication
Published : 20 December 2022
e-ISSN : 2347-470X
Page(s) : 1140-1145
Abstract
With the development of industrial economy, more and more enterprises use machine vision and artificial intelligence to replace manual detection. Therefore, the research of steel surface defect detection based on artificial intelligence is of great significance to promote the rapid development of intelligent factory and intelligent manufacturing system. In this paper, Yolov5 deep learning algorithm is used to build a classification model of steel surface defects to realize the classification and detection of steel surface defects. At the same time, on the basis of Yolov5, combined with the attention mechanism, the backbone network is improved to further improve the classification model of steel surface defects. The experiment shows that the Recall and mAP of improved Yolov5 perform better on the steel surface defect data set. Compared with Yolov5, the number of C3CA-Yolov5 parameters decreased by 13.02%, and the size of pt files decreased by 12.72%; the number of C3ECA-Yolov5 parameters decreased by 13.36%, and the size of pt files decreased by 13.22%.
Keywords: Machine Vision, Artificial Intelligence, Deep learning, Steel surface defects, Attention mechanism.
Fei Ren, School of Information Technology, Mapua University, Manila, Philippines; Email: renfeivision@outlook.com
GuangRong Wang, Sinoma (Nanjing) Mining Research Institute Co., Ltd, Nanjing, China; Email: 2058087205@qq.com
ZhiQi Hu, Sinoma Mining Construction Co., Ltd., Nanjing, China; Email: rf1314@vip.qq.com
MinNing Wu, School of Information Engineering, Yulin University, Yulin, Shaanxi; Email: cvvision@foxmail.com
Madhavi Devaraj*, School of Information Technology, Mapua University, Manila, Philippines; Email: madhavidevaraj@gmail.com
-
[1] Shen Xizhong & Wu Di. (2022). Detection of small defects on the surface of aluminum alloy based on Yolo Journal of Zhejiang University of Technology (04), 372-380.[Cross Ref]
-
[2] Lou Xudong, Cao songxiao, Jiang Qing, Xu Zhipeng & Tang Jianbin. (2022). Detection method of installation hole defect of expansion valve based on machine vision Machine tools and hydraulics (13), 90-96.[Cross Ref]
-
[3] Li Ke, Wu Zhongqing, Ji Yong & Su Lei. (2022). Improving the detection method of weld bubble defect in u-net chip X-ray image Journal of Huazhong University of science and Technology (NATURAL SCIENCE EDITION) (06), 104-110. Doi: 10.13245/j.hust.220613.[Cross Ref]
-
[4] Erozan Ahmet Turan and Bosse Simon and Tahoori Mehdi B. (2021). Defect Detection in Transparent Printed Electronics Using Learning-Based Optical Inspection. IEEE TRANSACTIONS ON VERY LARGE-SCALE INTEGRATION (VLSI) SYSTEMS, 29(8), pp. 1505-1517. [Cross Ref]
-
[5] Kento Nakashima et al. (2021). Defect detection in wrap film product using compact convolutional neural network. Artificial Life and Robotics, 26(3), pp. 1-7. [Cross Ref]
-
[6] Sun Yuhang et al. (2022). Vision-Based Detection of Bolt Loosening Using Yolov5. Sensors, 22(14), pp. 5184-5184. [Cross Ref]
-
[7] Chiriboga Matthew,Green Christopher M.,Hastman David A.,Mathur Divita,Wei Qi,Díaz Sebastían A& Veneziano Remi.(2022).Rapid DNA origami nanostructure detection and classification using the Yolov5 deep convolutional neural network. Scientific Reports (1).doi:10.1038/S41598-022-07759-3.[Cross Ref]
-
[8] Sozzi Marco et al. (2022). Automatic Bunch Detection in White Grape Varieties Using YOLOv3, YOLOv4, and Yolov5 Deep Learning Algorithms. Agronomy, 12(2), pp. 319-319.[Cross Ref]
-
[9] Nguyen HungCuong et al. (2022). Unified End-to-End Yolov5-HR-TCM Framework for Automatic 2D/3D Human Pose Estimation for Real-Time Applications. Sensors, 22(14), pp. 5419-5419.[Cross Ref]
-
[10] Q. Hou, D. Zhou and J. Feng, "Coordinate Attention for Efficient Mobile Network Design," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 13708-13717, doi: 10.1109/CVPR46437.2021.01350.[Cross Ref]
-
[11] Pikun Wang et al. (2022). Unmanned aerial vehicles object detection based on image haze removal under sea fog conditions. IET Image Processing, 16(10), pp. 2709-2721. [Cross Ref]
-
[12] Gu Ran,Wang Guotai,Song Tao,Huang Rui,Aertsen Michael,Deprest Jan... & Zhang Shaoting.(2020).CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation.. IEEE transactions on medical imaging. doi:10.1109/TMI.2020.3035253.[Cross Ref]
-
[13] Wang Q.,Wu B.,Zhu P.,Li P.,Zuo W. & Hu Q..(2020).ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. doi:10.1109/CVPR42600.2020.01155.[Cross Ref]
-
[14] Qu Zhong,Zhang Run & Bao Kanghua.(2021).A keypoint‐based object detection method with wide dual‐path backbone network and attention modules. IET Image Processing (8). doi:10.1049/IPR2.12152.[Cross Ref]
-
[15] oxu Qia, Qiao Xu, Liu Changchun, Wang Xinpei, Liu YuanYuan, Yao Lianke & Zhang Huan.(2021).Automated ECG classification using a non-local convolutional block attention module. Computer Methods and Programs in Biomedicine (prepublish). doi:10.1016/J.CMPB.2021.106006.[Cross Ref]
-
[16] Prof. Kalyani Kurundkar and Dr. G. A. Vaidya (2021), Application of HFPSO-TOPSIS approach for optimally locating and sizing of reactive power compensating devices for voltage control ancillary service. IJEER 9(3), 16-26. DOI: 10.37391/IJEER.090301.[Cross Ref]
-
[17] Swarnima Singh, Vikash Yadav (2021), An Improved Particle Swarm Optimization for Prediction of Accident Severity. IJEER 9(3), 42-47. DOI: 10.37391/IJEER.090304.[Cross Ref]
-
[18] Dr. J. S. Awati, Prof. S.S. Patil and Dr. M.S. Kumbhar (2021), Smart Heart Disease Detection using Particle Swarm Optimization and Support Vector Machine. IJEER 9(4), 120-124. DOI: 10.37391/IJEER.090405.[Cross Ref]
Fei Ren, GuangRong Wang, ZhiQi Hu, MinNing Wu and Madhavi Devaraj (2022), Research on Steel Surface Defect Detection Algorithm Based on Improved Deep Learning. IJEER 10(4), 1140-1145. DOI: 10.37391/IJEER.100461.