A Novel Pixel-Wise Defect Inspection Method Based on Stable Background Reconstruction
Chengkan Lv, Fei Shen, Zhengtao Zhang, De Xu, Yonghao He
Abstract
In this article, an anomaly detection method based on background reconstruction is proposed to perform defect inspection on the texture surface of the industrial products. This method consists of two modules: 1) an autoencoder integrated with a generative adversarial network is utilized to reconstruct the textured background of the original image as a defect-free reference. Specifically, extra anomalous images are introduced and a mapping method of anomaly is given to improve the stability of reconstruction. 2) A U-net based inspection network is trained to perform pixel-wise analysis of the differences between the original and the reconstructed defect-free image. During these processes, only artificial synthesized defective images are utilized to train the model without any real defective samples. A series of experiments are conducted on several texture image data sets and the industrial production line. The experimental results reveal the effectiveness and versatility of the proposed method.