Histogram Interpolation Methods for Image Contrast Enhancement

DOI HANDLE Web Site Open Access
  • Yu, Hengjun
    Department of Communication Design Science, Kyushu University
  • Inoue, Kohei
    Department of Communication Design Science, Kyushu University
  • Hara, Kenji
    Department of Communication Design Science, Kyushu University
  • Urahama, Kiichi
    Department of Communication Design Science, Kyushu University

Search this article

Abstract

Histogram equalization (HE) is a well-known technique for image contrast enhancement. However, HE frequently over-enhances the contrast of a given image to produce false contours in the enhanced image. One of the reasons for the production of false contours is the sparseness of the equalized histogram, which means that there exist gaps in continuous-tone. In this paper, we propose three methods for interpolating the sparse histogram obtained by HE, and utilize the interpolated histograms as the target ones for histogram specification or histogram matching, which transforms the histogram of a given image into the specified target histogram. Filling the gaps in equalized histogram by interpolation, we can reduce the occurrence of false contours. Experimental results show that the proposed methods can alleviate the over-enhancement of the contrast, which occurs frequently when we use HE. We also evaluate the quality of contrast-enhanced images by using three image quality measures, where the proposed methods achieve better performance than HE in many cases.

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top