Fu Guizhong, Zhang Zengguang, Le Wenwu, Li Jinbin, Zhu Qixin, Niu Fuzhou, Chen Hao, Sun Fangyuan, Shen Yehu
School of Mechanical Engineering, Suzhou University of Science and Technology, Suzhou, China.
College of Mechanical and Electrical Engineering, Shihezi University, Shihezi, China.
Front Neurorobot. 2023 Feb 14;17:1096083. doi: 10.3389/fnbot.2023.1096083. eCollection 2023.
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.
表面缺陷检测是实现产品质量检测的一项重要技术。在本研究中，我们开发了一种创新的多尺度池化卷积神经网络，以完成高精度的钢表面缺陷分类。该模型基于SqueezeNet构建，并在NEU无噪声和有噪声测试集上进行了实验。类激活映射可视化证明，多尺度池化模型能够在多个尺度上准确捕捉缺陷位置，不同尺度的缺陷特征信息可以相互补充和强化，从而获得更稳健的结果。通过T-SNE可视化分析发现，该模型的分类结果类间距离大、类内距离小，表明该模型具有较高的可靠性和较强的泛化能力。此外，该模型尺寸小（3MB），在NVIDIA 1080Ti GPU上运行速度高达130FPS，适用于具有高实时性要求的应用。
