Defective samples simulation through adversarial training for automatic surface inspection

Abstract

Deep learning has shown great potential in machine vision. However, introducing deep learning to automated surface inspection is still a challenging task because it depends heavily on the quality of training samples, especially the defective samples. In this paper, a general defective samples simulation method based on generative adversarial nets (GAN) is proposed to deal with the limitation of defective samples in production. Under the GAN framework, the simulative network with encoder–decoder architecture is proposed. Further, the simulative network and discriminative network are trained adversarially under the proposed regional training strategy, which gives priority to the translation of the defective area. Finally, the defect-free area is refined through wavelet fusion. This method requires a small number of defective training samples, and can generate simulative defects of specified shapes and types and meanwhile obtain the pixel-wise ground truth. The simulative samples can be used directly for training of deep learning based automated surface inspection tasks. We conduct experiments on four datasets. The experimental results show that our method can generate defective samples of higher quality than general image translation methods. Applying this method to surface defect inspection can significantly improve the effect of defect inspection model based on deep learning.