Abstract
Analyses of images acquired in dusty environments show that the images tend to have noise, blur, a small dynamic range, low contrast, diminished blue components, and high red components. The goals of this paper are to develop a modeling of dust noise on ordinary images and formulating enhancement and restoration strategy to improve the quality of dusty images using a sequence of image processing steps. This paper proposes that the dust noise model on ordinary images consisting of the atmospheric turbulence-blurring model, adjusting image brightness, and simulating real dust images colors contrasts. In addition, an automatic color correction algorithm consisting of image restoration using the Wiener filter, luminance stretching using YCbCr color model, and enhancing the image contrast using a modified homomorphic filter. Enhancement experiments are conducted on real and simulated 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, a statistical adaptive algorithm, 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.