Non-linear masking based contrast enhancement via illumination estimation

Soonyoung Hong, Minsub Kim, Moon Gi Kang

Research output: Contribution to journalConference article

Abstract

Contrast enhancement which is an important part of digital image processing has been studied for a long time and widely used in various fields such as digital photography or medical imaging. The purpose of contrast enhancement is to improve the overall contrast of the image and details on the local area. Contrast enhancement algorithms are classified into histogram based methods, tone mapping based methods, and retinex theory based methods. Particularly, retinex theory is widely applied at the spatial domain contrast enhancement. In this paper, we propose the contrast enhancement algorithm using the estimated illumination. Different from conventional retinex based algorithms, the estimated illumination serves as the tone mapping criterion and masked with original image. The intensity of estimated illumination image is adaptively modulated according to original image to improve the contrast of image effectively. Experimental results show that both global and local contrast are enhanced simultaneously with the proposed algorithm. Objective assessment using performance metrics also shows that the proposed method has the highest scores compared to the conventional methods.

Original languageEnglish
Article number389
JournalIS and T International Symposium on Electronic Imaging Science and Technology
DOIs
Publication statusPublished - 2018 Jan 1
Event16th Image Processing: Algorithms and Systems Symposium 2018 - Burlingame, United States
Duration: 2018 Jan 282018 Feb 1

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Fingerprint Dive into the research topics of 'Non-linear masking based contrast enhancement via illumination estimation'. Together they form a unique fingerprint.

  • Cite this