Computational ghost imaging using deep learning

OPTICS COMMUNICATIONS

卷:413

Article

Shimobaba, Tomoyoshi¹  Endo, Yutaka²  Nishitsuji, Takashi³  Takahashi, Takayuki¹  Nagahama, Yuki¹  Hasegawa, Satoki¹  Sano, Marie¹  Hirayama, Ryuji¹  Kakue, Takashi¹  Shiraki, Atsushi¹  Ito, Tomoyoshi¹ 

[1] Chiba Univ, Grad Sch Engn, Inage Ku, 1-33 Yayoi Cho, Chiba 2638522, Japan

[2] Kanazawa Univ, Inst Sci & Engn, Kakuma Machi, Kanazawa, Ishikawa 9201192, Japan

[3] Mitsubishi Electr Corp, Informat Technol R&D Ctr, 5-1-1 Ofuna, Kamakura, Kanagawa 2478501, Japan

关键词: Computational ghost imaging;    Ghost imaging;    Deep learning;   

DOI  :  10.1016/j.optcom.2017.12.041

来源: Elsevier

【 摘 要 】

Computational ghost imaging (CGI) is a single-pixel imaging technique that exploits the correlation between known random patterns and the measured intensity of light transmitted (or reflected) by an object. Although CGI can obtain two-or three-dimensional images with a single or a few bucket detectors, the quality of the reconstructed images is reduced by noise due to the reconstruction of images from random patterns. In this study, we improve the quality of CGI images using deep learning. A deep neural network is used to automatically learn the features of noise-contaminated CGI images. After training, the network is able to predict low-noise images from new noise-contaminated CGI images. (C) 2017 Elsevier B.V. All rights reserved.

【 授权许可】

Free