[2Xin5] インタラクティブ1

[2Xin5-06] Classification of X-ray inspection image samples with ambiguous appearances

〇Yasuhisa Kitai¹, Yoshiki Chigira¹, Teruaki Saitoh¹, Naoki Kurita¹, Yuichi Ishibashi², Toshinari Kamakura² (1.Oki Electric Industry Co., Ltd., 2.Chuo University)

Keywords:Manufacturing, Visual Inspection

In recent years, development of AI technology has been remarkable. It is expected that achievements of AI technology will be applied to real world, such as visual inspection in factories. However, in sensory inspection that relies on human senses such as visual inspection, it is difficult to define the limit samples. In this paper, we consider clear normally and anomaly samples to improve the efficiency of the process of visual inspection. We propose a method of constructing a data set consisting of only clear normally and anomaly samples and a method of expressing samples with ambiguous appearance as continuous numerical values from a model that has learned from clear normally and anomaly samples. As a result, we confirmed that the time to label ground truth was reduced and samples with ambiguous appearance changed continuously according to the inferred score.