Abstract: This paper describes the problem of visibility of outdoor images under haze and poor light condition. Visibility is a very important issue in case of computer based surveillance, crime analysis, driver assistance system designs etc. The most important challenge related to visibility is the atmospheric haze and poor lighting. The problem becomes more challenging if haze is too dense and lighting during night is extremely poor. The image processing is the vast emerging field in the era of technology of machine vision, machine intelligence and automation for real time processing or the post processing of the image captured in different atmospheric conditions. The image captured in the outdoor scene are highly degraded due to the poor lighting condition or over lighting condition or due to the presence of different suspension particle like the water droplets or dust particles. So due to these particles the irradiance coming from the object is scattered or absorbed. And hence the phenomena of haze, smoke and fog occurs. The haze removal is very essential in the field of image processing because the different computer vision algorithm assumes the input image as the original scene radiance or scene reflectance. But in most outdoor processing the images are degraded due to hazy, hence the input image is hazy image not the original radiance. In this paper we presented a technique Dark channel prior and Adaptive Histogram Equalization to improve visibility of outdoor images for different atmospheric condition. We have calculated performance parameters such as RMSE, PSNR and correlation coefficient.

Keywords: haze, poor lighting, dark channel prior method, adaptive histogram equalization, MSE, PSNR.