適応的Retinexモデルによるカラー画像の見えの改善

概要

論文の詳細を見る
The electronic camera can't catch the details in the heavy change of highlight and shadow, while human vision responses to very wide dynamic ranges. Retinex vision model controls the scene dynamic range automatically not by "pixel-to-pixel" but by "space-to-pixel" process like as human vision. This paper proposes an Adaptive Scale-Gain Retinex model and discusses the design of optimum parameters based on visual appearance experiments.
一般社団法人映像情報メディア学会の論文