GAによる携帯カメラ映像からの高コントラスト画像変換

概要

論文の詳細を見る
Even if the contrast of a scene images is not good, a single image that has good contrast can be generated by the accumulation of plural frames. However, the scene images must be shot by a fixed camera. This paper proposes a method to generate a single image with good contrast from scene images with low contrast that are shot by a portable video camera carried by hand. The partial frames are selected from all frames by the genetic algorithm. These frames are accumulated and the output image is generated by the liner transform of gray-levels. The individual fitness is evaluated by the total value of liner gradients in the generated output image. The experimental results show that the generated images by the proposed method had good contrast, clearness and less noises in comparison with the generated images by the conventional methods.
2003-07-01