Improvement of segmentation accuracy using single-class images

Abstract

It is necessary to collect training data to inspect for foreign substances using segmentation. But to collect and annotate images of foreign substances mixed in normal products is costly. It is easy to collect and annotate images of only normal products and images of only foreign substances. In this study, instead of training with many images of foreign substances mixed in normal products, we propose training with images of only normal products, images of only foreign substances and a few images of foreign substances mixed in normal products. As a result, the proposed training method improved inspection accuracy, while reducing annotation cost.