Image contrast enhancement using optimum sub-histograms modification and preserving brightness levels mean without losing image specification

Abstract

Histogram modification is one of the well- known and most effective techniques in increasing contrast and image quality enhancement. But, in some cases, traditional histogram modification would increase image contrast too much and cause image details to be lost. In this article, a new histogram modification method has been proposed that contains a combination of histogram division part and brightness level transferring part. In histogram division part, image histogram will be divide into smaller optimum subunits according to mean value and standard deviation. This division is controlled automatically by using PSNR criterion. In the second part, with applying local cumulative probability distribution function for each of subunits of histogram, we will reach the enhanced image. Experimental results shows that, this method would not only keep visual details of histogram, but also enhance image contrast.