Share Email Print

Proceedings Paper

Object segmentation using skin color and motion information
Author(s): Eui-Yoon Chung; Ho-Keun Lee; Hyung Suk Kim; Yeong-Ho Ha
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents an effective object segmentation method for object-oriented coding. The process is composed of facial region detection using skin color and changed region detection using motion information. The image is then segmented between moving objects and background using motion estimation. The facial regions are detected using skin color, the data for which is obtained from the u, v image. This data is then used as a threshold to segment the facial region. The image is also segmented into changed regions using motion information. After combining these results, the final image is segmented between moving objects and background. This method is more efficient due to two factors, color and motion. Experimental results show that the proposed method can significantly improve the image quality.

Paper Details

Date Published: 29 December 2000
PDF: 9 pages
Proc. SPIE 4310, Visual Communications and Image Processing 2001, (29 December 2000); doi: 10.1117/12.411854
Show Author Affiliations
Eui-Yoon Chung, Kyungpook National Univ. (South Korea)
Ho-Keun Lee, Kyungpook National Univ. (South Korea)
Hyung Suk Kim, Kyungpook National Univ. (South Korea)
Yeong-Ho Ha, Kyungpook National Univ. (South Korea)

Published in SPIE Proceedings Vol. 4310:
Visual Communications and Image Processing 2001
Bernd Girod; Charles A. Bouman; Eckehard G. Steinbach, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?