loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
17th International Conference on Pattern Recognition (ICPR'04) - Volume 1
Non-contrast Based Edge Descriptor for Image Segmentation
Cambridge UK
August 23-August 26
ISBN: 0-7695-2128-2
ASCII Text
x 
 
Byung-Gyu Kim, Pyeong-Soo Mah, Dong-Jo Park, Jik-Han Jung, Ju-Seok Park, "Non-contrast Based Edge Descriptor for Image Segmentation," Pattern Recognition, International Conference on, vol. 1, pp. 572-575, 17th International Conference on Pattern Recognition (ICPR'04) - Volume 1, 2004.
 
 
BibTex
x
 
@article{ 10.1109/ICPR.2004.1334205,
author = {Byung-Gyu Kim and Pyeong-Soo Mah and Dong-Jo Park and Jik-Han Jung and Ju-Seok Park},
title = {Non-contrast Based Edge Descriptor for Image Segmentation},
journal ={Pattern Recognition, International Conference on},
volume = {1},
year = {2004},
issn = {1051-4651},
pages = {572-575},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2004.1334205},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Pattern Recognition, International Conference on
TI - Non-contrast Based Edge Descriptor for Image Segmentation
SN - 1051-4651
SP572
EP575
A1 - Byung-Gyu Kim,
A1 - Pyeong-Soo Mah,
A1 - Dong-Jo Park,
A1 - Jik-Han Jung,
A1 - Ju-Seok Park,
PY - 2004
KW - null
VL - 1
JA - Pattern Recognition, International Conference on
ER -
 
Byung-Gyu Kim, Embedded S/W Technology Center, ETRI, Korea
Pyeong-Soo Mah, Embedded S/W Technology Center, ETRI, Korea
Dong-Jo Park, KAIST, Korea
Jik-Han Jung, KAIST, Korea
Ju-Seok Park, KAIST, Korea
We present an efficient object segmentation strategy based on edge information to assist object-based video coding, motion estimation and motion compensation for the MPEG system. Two parameters are introduced and described based on edge information from the analysis of a local histogram. Using these features, a non-contrast based edge function is defined to generate an edge information map, which can be thought as a gradient image. Then, an improved marker-based region growing and merging techniques are derived to separate image regions. The proposed algorithm is tested on several standard images and demonstrates high reliability for object segmentation.
Citation:
Byung-Gyu Kim, Pyeong-Soo Mah, Dong-Jo Park, Jik-Han Jung, Ju-Seok Park, "Non-contrast Based Edge Descriptor for Image Segmentation," icpr, vol. 1, pp.572-575, 17th International Conference on Pattern Recognition (ICPR'04) - Volume 1, 2004
Usage of this product signifies your acceptance of the Terms of Use.