Linearly quantile separated weighted dynamic histogram equalization for contrast enhancement. (August 2017)

• Record Type: Journal Article
• Authors: Gupta, Bhupendra; Agarwal, Tarun Kumar
• Is Part Of: Computers & electrical engineering. Volume 62(2017)
• Page Start: 360
• Page End: 374
• Publication Date: 2017-08
• Subjects: Histogram equalization -- Image contrast enhancement -- Power law function -- Histogram weighting -- Quantiles -- Brightness preservation; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.01.010
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Linear segmentation of histogram in sub-histogram based on quantiles of input image. Use of complete spectrum of the grey level for enhancement. Brightness preserving contrast enhancement. Complete control over the level of contrast enhancement. Graphical abstract: Abstract: Contrast-enhancement is a prerequisite of various image-processing and computer-vision applications. When we employ contrast-enhancement tools based on histogram equalization, the mean-shift problem commonly arises. In this work, we propose a new approach to contrast enhancement which overcomes the mean-shift problem. In the proposed approach, we suggest a quantile-based division of the histogram of a given image, which can be used across the entire spectrum of grey level for contrast-enhancement. Due to its non-recursive nature, the proposed approach is computationally less expensive than many other methods. Experimental results show that the proposed method performs better than other existing methods available in related literature. Further, this method preserves image brightness more accurately and takes less time as compared to prevailing state of art approaches.