Face segmentation using combined bottom-up and top-down saliency maps

Z Q Seak; Li-Minn Ang; K P Seng

doi:10.1109/ICCSIT.2010.5563915

Back

Face segmentation using combined bottom-up and top-down saliency maps

Conference paper

Peer reviewed

Face segmentation using combined bottom-up and top-down saliency maps

Z Q Seak, Li-Minn Ang and K P Seng

IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010, pp.477-480

International Conference on Computer Science and Information Technology, 3rd ( Chengdu, China, 09-Jul-2010–11-Jul-2010)

Institute of Electrical and Electronics Engineers

2010

DOI: https://doi.org/10.1109/ICCSIT.2010.5563915

Files and links (1)

url

https://doi.org/10.1109/ICCSIT.2010.5563915View

Published Version

Abstract

Bottom-up visual attention

Face segmentation

Saliency map

Top-down perception

Visual attention

This paper presents a simple color based segmentation technique for faces. The proposed technique utilizes saliency maps and incorporates both top-down (data driven) and bottom-up saliency methods to generate the saliency map used in the segmentation phase. The top-down approach uses skin color data obtained from a training database to bias the skin color saliency map while the bottom up approach utilizes both the intensity and color features maps from the test image. The saliency map is computed from the center sound difference and normalization of the feature maps from both systems. Finally, a square moving window function is used to determine the point with the highest energy in the saliency map, which is marked as the facial region. The system shows good performance for subjects in both simple and complex backgrounds, as well as varying illumination conditions and skin color variances.

Details

Title: Face segmentation using combined bottom-up and top-down saliency maps
Authors: Z Q Seak (Author) - University of Nottingham Malaysia Campus
Li-Minn Ang (Author) - University of Nottingham Malaysia Campus
K P Seng (Author) - University of Nottingham Malaysia Campus
Publication details: IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010, pp.477-480
Conference details: International Conference on Computer Science and Information Technology, 3rd ( Chengdu, China, 09-Jul-2010–11-Jul-2010)
Publisher: Institute of Electrical and Electronics Engineers
Date published: 2010
DOI: 10.1109/ICCSIT.2010.5563915
ISSN: 1558-2256
ISBN: 9781424455409
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99513891002621
Output Type: Conference paper

Metrics

30 Record Views