Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching

There are no files associated with this record.

Title Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching
Author Chen, Luke; Gao, Yongsheng
Publication Title Computer Vision -- ECCV 2010 Proceedings, Part 3
Editor Kostas Daniilidis, Petros Maragos, Nikos Paragios
Year Published 2010
Place of publication Germany
Publisher Springer
Abstract Automatically recognizing human faces with partial occlusions is one of the most challenging problems in face analysis community. This paper presents a novel string-based face recognition approach to address the partial occlusion problem in face recognition. In this approach, a new face representation, Stringface, is constructed to integrate the relational organization of intermediate-level features (line segments) into a high-level global structure (string). The matching of two faces is done by matching two Stringfaces through a string-to-string matching scheme, which is able to efficiently find the most discriminative local parts (substrings) for recognition without making any assumption on the distributions of the deformed facial regions. The proposed approach is compared against the state-of-the-art algorithms using both the AR database and FRGC (Face Recognition Grand Challenge) ver2.0 database. Very encouraging experimental results demonstrate, for the first time, the feasibility and effectiveness of a high-level syntactic method in face recognition, showing a new strategy for face representation and recognition.
Peer Reviewed Yes
Published Yes
Alternative URI http://dx.doi.org/10.1007/978-3-642-15558-1_36
ISBN 364215557X
Conference name 11th European Conference on Computer Vision (ECCV 2010)
Location Heraklion, Crete, Greece
Date From 2010-09-05
Date To 2010-09-11
URI http://hdl.handle.net/10072/36787
Date Accessioned 2010-11-04
Date Available 2011-03-04T07:02:54Z
Language en_AU
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Science, Environment, Engineering and Technology
Subject PRE2009-Computer Vision; PRE2009-Pattern Recognition
Publication Type Conference Publications (Full Written Paper - Refereed)
Publication Type Code e1

Show simple item record

Griffith University copyright notice