A new multiscale texture surface defect detection method based on convolutional neural network

Traditional computer defect detection methods usually focus on the handcrafted features, but these methods have many limitations. In this paper, an approach of texture surface defect detection based on convolution neural network (CNN) and wavelet analysis is proposed. The approach combines wavelet analysis with patches extraction, which can detect and locate many kinds of defects in complex texture background, especially tiny defects in large-scale images. It is evaluated on DAGM 2007 dataset and Micro surface defect database, the results demonstrate that it has a high accuracy in defect detection with only a small amount of training data.