主催: 電気・情報関係学会九州支部連合大会委員会
共催: 佐賀大学
会議名: 2021年度電気・情報関係学会九州支部連合大会
回次: 74
開催地: オンライン開催（大会本部：佐賀大学本庄キャンパス）
開催日: 2021/09/24 - 2021/09/25
In this paper, we perform the super resolution of sea surface temperature data with the enhanced super resolution generative adversarial network (ESRGAN) and with the super-resolution convolutional neural network (SRCNN) and residual-in-residual dense block network (RRDBNet) methods. The images generated with these methods are compared with high-resolution data using root mean square error (RMSE), learned perceptual image patch similarity (LPIPS), and perceptual index (PI) evaluation methods. RRDBNet has a better RMSE than SRCNN and ESRGAN. ESRGAN has a better LPIPS and PI than CNN methods.
