A multi-scale pooling convolutional neural network for accurate steel surface defects classification

Guizhong Fu; Zengguang Zhang; Wenwu Le; Jinbin Li; Qixin Zhu; Fuzhou Niu; Hao Chen; Fangyuan Sun; Yehu Shen

doi:10.3389/fnbot.2023.1096083

A multi-scale pooling convolutional neural network for accurate steel surface defects classification

Front Neurorobot. 2023 Feb 14:17:1096083. doi: 10.3389/fnbot.2023.1096083. eCollection 2023.

Authors

Guizhong Fu¹, Zengguang Zhang¹, Wenwu Le¹, Jinbin Li², Qixin Zhu¹, Fuzhou Niu¹, Hao Chen¹, Fangyuan Sun¹, Yehu Shen¹

Affiliations

¹ School of Mechanical Engineering, Suzhou University of Science and Technology, Suzhou, China.
² College of Mechanical and Electrical Engineering, Shihezi University, Shihezi, China.

Abstract

Surface defect detection is an important technique to realize product quality inspection. In this study, we develop an innovative multi-scale pooling convolutional neural network to accomplish high-accuracy steel surface defect classification. The model was built based on SqueezeNet, and experiments were carried out on the NEU noise-free and noisy testing set. Class activation map visualization proves that the multi-scale pooling model can accurately capture the defect location at multiple scales, and the defect feature information at different scales can complement and reinforce each other to obtain more robust results. Through T-SNE visualization analysis, it is found that the classification results of this model have large inter-class distance and small intra-class distance, indicating that this model has high reliability and strong generalization ability. In addition, the model is small in size (3MB) and runs at up to 130FPS on an NVIDIA 1080Ti GPU, making it suitable for applications with high real-time requirements.

Keywords: class activation map; convolutional neural network; defect classification; feature visualization; multi-scale.

Grants and funding

This research was supported by the National Natural Science Foundation of China (Nos. 52105526, 51975394, 61903269, and 51875380) and the China Postdoctoral Science Foundation (Nos. 2020M671383 and 2020M681517).