Image enhancement using wavelet decomposition, quadratic thresholding and Auto-Adaptive LUM filter

An image captured in a bad weather suffers from poor contrast. As one of the most common weather conditions, fog whitens the scenery that is the captured image and decreases the atmospheric visibility which leads to the decline of image contrast, gained by optical equipment and produces fuzzy look to the images. All the problems mentioned above might bring great difficulty to the image information extraction, outdoor image monitoring, automatic navigation, target identification, tracking and etc,.. Therefore, it is necessary that image captured in a bad weather or the foggy image is enhanced. In this paper, a new method for foggy image enhancement has been proposed, that integrates multilevel wavelet decomposition, the auto-adapted LUM filter, quadratic thresholding function and so on. Firstly, the multilevel wavelet decomposition is done to the image secondly low-frequency and high-frequency components of the image is obtained and finally the auto-adapted LUM filter is applied to low-frequency component. This new shrinkage function based on wavelet packet approximations turn out to be more flexible than the soft and hard-thresholding function and eventually carrying on wavelet restructuring to the processed components.