Abstract
The paper presents a novel approach to face recognition using Local Binary Patterns (LBP) with the novel soft chi square and soft power metrics. Results of intensive experiments on two public databases, FERET and AT&T, show that these new metrics are efficient and flexible for real-time face recognition applications. They can reduce time performance and also achieve high recognition rate.
Original language | English |
---|---|
Title of host publication | International Conference on Knowledge-Based and Intelligent Information and Engineering Systems |
Subtitle of host publication | Lecture Notes in Artificial Intelligence |
Editors | Andreas Kenig, Andreas Dengel, Knut Hinkelmann, Koichi Kise, Robert J Howlett, Lakhmi C Jain |
Place of Publication | Germany |
Publisher | Springer |
Pages | 436-445 |
Number of pages | 10 |
Volume | 6881 |
ISBN (Print) | 9783642238505 |
DOIs | |
Publication status | Published - 2011 |
Event | Knowledge-Based and Intelligent Information and Engineering Systems - Kaiserslautern, Kaiserslautern, Germany Duration: 12 Sept 2011 → 14 Sept 2011 |
Conference
Conference | Knowledge-Based and Intelligent Information and Engineering Systems |
---|---|
Abbreviated title | KES 2011 |
Country/Territory | Germany |
City | Kaiserslautern |
Period | 12/09/11 → 14/09/11 |