Abstract
Defect detection requires highly sensitive and robust inspection methods. This study shows that non-overlapping illumination patterns can improve the noise robustness of deep learning ghost imaging (DLGI) without modifying the convolutional neural network (CNN). Ghost imaging (GI) can be accelerated by combining GI and deep learning. However, the robustness of DLGI decreases in exchange for higher speed. Using non-overlapping patterns can decrease the noise effects in the input data to the CNN. This study evaluates the DLGI robustness by using non-overlapping patterns generated based on binary notation. The results show that non-overlapping patterns improve the position accuracy by up to 51%, enabling the detection of defect positions with higher accuracy in noisy environments.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Shoma Kataoka, Yasuhiro Mizutani, Tsutomu Uenohara, Yasuhiro Takaya, and Osamu Matoba
Appl. Opt. 61(23) 6714-6721 (2022)
Yuta Haruse, Teruaki Torii, Shintaro Sugimoto, and Yusuke Kasaba
OSA Continuum 4(1) 149-157 (2021)
Ziqi Gao, Xuemin Cheng, Junbai Yue, and Qun Hao
Opt. Express 30(25) 45759-45775 (2022)