Entropy based optimized weighted histogram equalization for Hazy Images

The contrast of an image is a feature which determines how image looks better visually. The Contrast enhancement is considered as one of the most important issues in image processing. The contrast of Hazy Images is very low. Haze is cloudiness of a product that is caused by scattering of light. Histogram equalization (HE) is one of the methods used for improving contrast. One drawback of HE have not preserve the brightness while enhancing the contrast because abrupt mean shift is occur during the process of equalization. Today many HE based methods is presented to overcome the problem of mean shift. But, they suffered from over-enhancement. In this paper a novel approach of histogram equalization is proposed which is called optimized weighted histogram equalization using Genetic algorithm (GWHE). The central idea of paper is to modify the histograms by weighting process based on a normalized power law function. Genetic Algorithm (GA) is used to optimize the value of weighing constraints i.e. `a´ and `b´ based on entropy. The experimental results show that the proposed method does both enhancement and brightness preservation and thereby improves information of hazy images. Entropy of images is used as a fitness function in this work. For other performance assessment we have used in this paper Peak Signal to Noise Ratio (PSNR) and Structure Similarity Index (SSEVI).