Abstract
To address the technical shortcomings of conventional histogram equalization (HE), such as over-enhancement and artifacts, we propose a histogram-constrained and contrast-tunable HE technique for digital image enhancement. Firstly, the input image histogram is partitioned into two parts, the main histogram and the constrained histogram, by a cumulative probability density threshold; second, the main histogram is redistributed equally in the whole grayscale range; and finally, the nonlinearity of the constrained histogram is mapped to the main histogram. The experimental averages show that the values of the two metrics, information entropy and MS-SSIM, processed by the algorithms in this paper, are more accurate compared to the other six excellent algorithms.
Funding Information
  • National Key Research and Development Program of China (2016YFD0700400)

This publication has 34 references indexed in Scilit: