Siamese-RCNet: Defect Detection Model for Complex Textured Surfaces with Few Annotations

作者：Dandan Guo, Chunying Zhang, Guanghui Yang, Tao Xue, Jiang Ma, Lu Liu, Jing Ren · 发表于：Electronics · 年份：2024 · DOI：10.3390/electronics13244873 · 被引用次数：4 · 研究领域：Industrial Vision Systems and Defect Detection、Surface Roughness and Optical Measurements、Advanced Neural Network Applications

The surface texture of objects in industrial scenes is complex and diverse, and the characteristics of surface defects are often very similar to the surrounding environment and texture background, so it is difficult to accurately detect the defect area. However, when deep learning technology is used to detect complex texture surface defects, the detection accuracy is not high, due to the lack of large-scale pixel-level label datasets. Therefore, a defect detection model Siamese-RCNet for complex texture surface with a small number of annotations is proposed. The Cascade R-CNN target detection network is used as the basic framework, making full use of unlabeled image feature information, and fusing the nonlinear relationship learning ability of Siamese network and the feature extraction ability of the Res2Net backbone network to more effectively capture the subtle features of complex texture surface defects. The image difference measurement method is used to calculate the similarity between different images, and the attention module is constructed to weight the feature map of the feature extraction pyramid, so that the model can focus more on the defect area and suppress the influence of complex background texture area, so as to improve the accuracy of detection. To verify the effectiveness of the Siamese-RCNet model, a series of experiments were carried out on the DAGM2007 dataset of weakly supervised learning texture surface defects for industrial optical inspection. The res...