Back to articles
Articles
Volume: 3 | Article ID: art00033
Image
Highlight Removal in Endoscope Images
Vladimir Bochko
Yoichi Miyake
  DOI :  10.2352/CGIV.2006.3.1.art00033  Published Online :  January 2006
Abstract

In this paper, we propose an efficient algorithm for highlight removal in endoscope images. According to the analysis the endoscope images are presented by several kinds of regions and the dichromatic reflection model is not valid for the whole image. However it is possible to segment the image using machine learning algorithms and extract only the body and highlight reflection regions for which the dichromatic reflection model is relevant and then the highlight removal technique is applied. We present the experimental results confirming the method's feasibility.

Journal Title : Conference on Colour in Graphics, Imaging, and Vision
Publisher Name : Society of Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151, USA
Subject Areas :
Views 18
Downloads 3
 DOI 10.2352/CGIV.2006.3.1.art00033
 articleview.views 18
 articleview.downloads 3
  Cite this article 

Vladimir Bochko, Yoichi Miyake, "Highlight Removal in Endoscope Images"  in Proc. IS&T CGIV 2006 3rd European Conf. on Colour in Graphics, Imaging, and Vision,  2006,  pp 167 - 171,  https://doi.org/10.2352/CGIV.2006.3.1.art00033

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2006
72010351
Conference on Colour in Graphics, Imaging, and Vision
conf colour graph imag vis
2158-6330
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA
2158-6330(20060101)2006:1L.167;1-
cgiv_v2006n1/splitsection33.xml
/ist/cgiv/2006/00002006/00000001/art00033
Articles
Highlight Removal in Endoscope Images
BochkoVladimir
MiyakeYoichi
01012006
2006
1
167
171
2006
In this paper, we propose an efficient algorithm for highlight removal in endoscope images. According to the analysis the endoscope images are presented by several kinds of regions and the dichromatic reflection model is not valid for the whole image. However it is possible to segment the image using machine learning algorithms and extract only the body and highlight reflection regions for which the dichromatic reflection model is relevant and then the highlight removal technique is applied. We present the experimental results confirming the method's feasibility.