Open AccessEntropy maximisation histogram modification scheme for image enhancement
Author(s) -
Wei Zhao,
Lidong Huang,
Jun Wang,
Zebin Sun
Publication year - 2015
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2014.0347
Subject(s) - histogram , entropy (arrow of time) , pixel , grey scale , artificial intelligence , computer science , pattern recognition (psychology) , mathematics , histogram matching , grey level , algorithm , image (mathematics) , physics , quantum mechanics
Contrast enhancement plays an important role in image processing applications. The global histogram equalisation (GHE)‐based techniques are very popular for their simpleness. In the author's study, the authors originally divide the GHE techniques into two steps, that is, the pixel populations mergence (PPM) step and the grey‐levels distribution (GLD) step. In the PPM step, the pixel populations of adjoining grey scales to be mapped to the same grey scale are merged firstly in input histogram. Then, the new grey scales are redistributed according to a corresponding transformation function in the GLD step. This division is meaningful because the entropy of enhanced image is only determined by pixel populations regardless of grey levels. Then, they prove the entropy of enhanced image is reduced because of mergence. Inspired by GHE, they propose a novel entropy maximisation histogram modication scheme, which also consists of PPM and GLD steps. However, the entropy is maximised, that is, the reduction of entropy is minimised under originally presented entropy maximisation rule in their PPM step. In the GLD step, they redistribute the grey scales in the merged histogram using a log‐based distribution function to control the enhancement level. Experimental results demonstrate the proposed method is effective.