Back to articles
Volume: 2 | Article ID: art00108
Learning to Display High Dynamic Range Images
  DOI :  10.2352/CGIV.2004.2.1.art00108  Published OnlineJanuary 2004

In this paper we present a novel method to map high dynamic range scenes to low dynamic range images for visualization. We formulate the problem as a quantization process and employ an adaptive learning strategy to ensure that the low dynamic range displays not only faithfully reproduce the original scenes but also are visually pleasing. This is achieved by the use of a competitive learning neural network that employs a frequency sensitive competitive learning mechanism. An L2 objective function ensures that the mapped low dynamic image preserves the relative visual contrast impressions of the original scene. A frequency sensitive competitive mechanism facilitates the full and even utilization of the limited displayable values. We present experimental results to demonstrate the effectiveness of the method in displaying a variety of high dynamic range scenes.

Subject Areas :
Views 1
Downloads 0
 articleview.views 1
 articleview.downloads 0
  Cite this article 

Jiang Duan, Guoping Qiu, Graham Finlayson, "Learning to Display High Dynamic Range Imagesin Proc. IS&T CGIV 2004 Second European Conf. on Colour in Graphics, Imaging, and Vision,  2004,  pp 542 - 547,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2004
Conference on Colour in Graphics, Imaging, and Vision
conf colour graph imag vis
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA