[17p-A37-1~6] CS.2 Code-sharing Session of 3.2 & 4.4

1:30 PM - 1:45 PM JST(4:30 AM - 4:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[17p-A37-1] Phase detection of phase-4-valued multiply recorded images using machine learning

〇Sota Aizawa¹, Ryushi Fujimura^1,2 (1.Utsunomiya Univ., 2.IIS, Univ. of Tokyo)

Keywords:

optical memory,holographic memory,machine learning

Holographic memory stores interference fringes of information light and reference light in a hologram and records different information overlaid in the same space by changing the angle of the reference light (angle multiplex recording). If the same reference light as the recording angle is incident during playback, the other images become noise and the false detection rate increases. In this study, we introduce machine learning using 3D convolutional layers to recover multiply recorded images and show that the detection accuracy is improved.