A SIAMESE NETWORK UTILIZING IMAGE STRUCTURAL DIFFERENCES FOR CROSS-CATEGORY DEFECT DETECTION

A machine learning based defect detection system generally requires a training procedure based on certain samples. In industry applications where there are variant product categories, a re-training upon category changing could be time expensive and unacceptable. In this work, a two-layer neural networks are proposed for cross-category defect detection without re-training. Different from traditional neural networks, the proposed method learns differences from image-pairs containing certain structural similarity rather than from a single image. With the assumption that different categorical objects could share certain structural similarity indicated by these learned image pairwise differences, a pairwise Siamese neural network is used in the proposed neural networks for defect detection. The cross-category capability of the proposed method is evidenced via experiments based on real-world factory datasets.