Optimal Histogram Modification scheme for image contrast enhancement using Otsu's optimality method

This paper proposes a new technique, a Optimal Histogram Modification using Otsu's optimality principle (OHM) for the purpose of contrast enhancement as well as preserving the brightness for any given input image. First, the method smoothes the input histogram by using Gaussian filter. Then, the smoothed histogram is partitioned into two sub-histograms based on a threshold which is obtained by calculating minimum difference between input and output mean. Finally, optimal weighing constraints are formulated based on the histograms of these sub-images and then these two histograms are equalized independently. The optimal values of those constraints are calculated using Otsu's optimality principle. The union of these two sub-images produces a brightness preserved contrast enhanced output image. This mechanism enhances the contrast of the input image better than its existing contemporary HE methods. The performance of the proposed method is measured in terms of Discrete Entropy and Absolute Mean Brightness Error.