A Surface Defect Detection Method Based on Positive Samples

Abstract

Surface defect detection and classification based on machine vision can greatly improve the efficiency of industrial production. With enough labeled images, defect detection methods based on convolution neural network have achieved the detection effect of state-of-art. However in practical applications, the defect samples or negative samples are usually difficult to be collected beforehand and manual labelling is time-consuming. In this paper, a novel defect detection framework only based on training of positive samples is proposed. The basic detection concept is to establish a reconstruction network which can repair defect areas in the samples if they are existed, and then make a comparison between the input sample and the restored one to indicate the accurate defect areas. We combine GAN and autoencoder for defect image reconstruction and use LBP for image local contrast to detect defects. In the training process of the algorithm, only positive samples is needed, without defect samples and manual label. This paper carries out verification experiments for concentrated fabric images and the dataset of DAGM 2007. Experiments show that the proposed GAN+LBP algorithm and supervised training algorithm with sufficient training samples have fairly high detection accuracy. Because of its unsupervised characteristics, it has higher practical application value.