High efficient contrast enhancement using parametric approximation

Yun Fu Liu, Jing Ming Guo, Bo Syun Lai, Jiann Der Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

24 Scopus citations

Abstract

In this study, a local contrast enhancement method, namely Parametric-Oriented Histogram Equalization (POHE), is proposed to effectively yield enhanced results. In general, the grayscale distribution of a specific region in an image can be modeled with a kernel function such as the Gaussian, and thus the corresponding estimated cumulative distribution function (cdf) can be considered as the transformation function for contrast enhancement. The required parameters, however, still need to access all of the pixels in the corresponding region, and thus consume a huge amount of computations. To cope with this, the concept of integral image is adopted to effectively derive the required parameters. In the experimental results, former well-known speed-oriented methods are adopted for comparison, and the results demonstrate that the proposed methods can provide high practical value for biometric and tracking/detection these active issues who desire high efficiency.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages2444-2448
Number of pages5
DOIs
StatePublished - 18 10 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 26 05 201331 05 2013

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Country/TerritoryCanada
CityVancouver, BC
Period26/05/1331/05/13

Keywords

  • Image enhancement
  • contrast enhancement
  • histogram equalization
  • integral image
  • parametric-oriented histogram equalization

Fingerprint

Dive into the research topics of 'High efficient contrast enhancement using parametric approximation'. Together they form a unique fingerprint.

Cite this