Image clearness method based on improved Retinex

In order to improve the visibility of the aerial image with low contrast and lJow brightness, a changing scale Retinex algorithm based on scene depth information is studied in this paper. Firstly, the original image is converted from RGB color space to HIS color space, which is more comfortable for human eye features. Then the H component is ensured invariantly while the S component is stretched linearly by an adaptive stretching algorithm; the I component is adjusted by an improved Retinex algorithm, the scale of Retinex is changing according to the scene depth information of the image, which can provide significant improvement in contrast and brightness and enrich the detail information. Experiment result shows that the proposed algorithm has good clearness effect and fast speed, especially for the aerial images with greatly difference in scene depth.