Vague color image enhancement on fractional differential and improved retinex

Using aerial color images or remote sensing color images to obtain the earth surface information is an important way for gathering geographic information. In order to improve visibility in the poor quality weather for aerial color images, a changing scale Retinex algorithm based on fractional differential and depth map is proposed. After a new fractional differential operation, it requires the image dark channel prior treatment to obtain the estimated depth map. Then according to the depth map, Retinex scales are calculated in each part of the image. Finally the single scale Retinex transform is performed to obtain the enhanced image. Experimental results show that the studied algorithm can effectively improve the visibility of an aerial color image without halo phenomena and color variation which happens if using a similar ordinary algorithm. Compared with the He’s algorithm and others, the new algorithm has the faster speed and better image enhancement effect for the images that have greatly different scene depths.