DocumentCode :
2531129
Title :
Face Recognition using 3D Line Edge Map Robust to Expression Changes and Occlusions
Author :
Kim, Hye-Mi ; Shin, Ho-Chul ; Kim, Seong Dae
Author_Institution :
Electron. & Telecommun. Res. Inst.
Volume :
1
fYear :
2007
fDate :
12-14 Feb. 2007
Firstpage :
357
Lastpage :
362
Abstract :
We propose new face recognition algorithm using 3D line edge map as combining 3D information on the edge obtained by stereo camera and the conventional line edge map algorithm. As a similarity measure of 3D line edge map, weighted partial and spatially well-localized line segment Hausdorff distance (WPSLHD) is proposed. WPSLHD is a measure which is robust to expression changes, facial occlusions, and depth outliers. The proposed face recognition system performances are evaluated under expression changes and facial occlusions.
Keywords :
face recognition; image sensors; matrix algebra; 3D line edge map algorithm; WPSLHD; expression changes; face recognition; facial occlusions; stereo camera; weighted partial and spatially well-localized line segment Hausdorff distance; Cameras; Computer science; Data mining; Face detection; Face recognition; Humans; Image segmentation; Lighting; Performance evaluation; Robustness; 3D Line Edge Map; 3D face recognition; line segment Hausdorff Distance; stereo images;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Communication Technology, The 9th International Conference on
Conference_Location :
Gangwon-Do
ISSN :
1738-9445
Print_ISBN :
978-89-5519-131-8
Type :
conf
DOI :
10.1109/ICACT.2007.358372
Filename :
4195151
Link To Document :
بازگشت