A statistical adaptive algorithm for dust image enhancement and restoration

Analyses of images acquired in dusty environments show that the images tend to have noise, blur, small dynamic ranges, low contrast, diminished blue components, and high red components. The goal of this paper is to develop a strategy to enhance such dusty images using a sequence of image processing steps. A statistical adaptive algorithm consisting of image restoration using the Wiener filter, contrast stretching using the RGB color model, intensity stretching using the HSI color model, and color cast removal using color balance, is introduced. Enhancement experiments are conducted on real dusty images and it is shown that the strategy is quite effective in enhancing dusty images. Furthermore the results are superior to those obtained through histogram equalization, gray world, and white patch algorithms. In addition, the complexity of the proposed algorithm is very low thus making it attractive for real time-image processing.