Modified Histogram Segmentation Bi-Histogram Equalization

Abstract

In the application of image processing, contrast enhancement is a major step. Conventional methods which are studied in contrast enhancement such as Histogram Equalization (HE) have not satisfactory results on many different low-contrast images and they also cannot automatically handle different images. These problems result of specifying parameters manually in order to produce high contrast images. In this paper, Modified Histogram Segmentation Bi-Histogram Equalization (MHSBHE) is proposed. In this study, histogram is modified before segmentation to improve the input image contrast. The proposed method accomplishes multi goals of preserving brightness, retaining the shape features of the original histogram and controlling excessive enhancement rate, suiting for applications of consumer electronics. MHSBHE avoids over-enhancement and generates images with natural improvement. Simulation results show that in terms of visual assessment, peak signal-to-noise (PSNR), average information content (entropy) and Absolute Mean Brightness Error (AMBE) the proposed method has better results compared to literature methods. The proposed method enhances the natural appearance of images especially in no static range images and the improved image is helpful in generation of the consumer electronic.