Novel Metrics for Face Recognition Using Local Binary Patterns

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

4 Citations (Scopus)

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 languageEnglish
Title of host publicationInternational Conference on Knowledge-Based and Intelligent Information and Engineering Systems
Subtitle of host publicationLecture Notes in Artificial Intelligence
EditorsAndreas Kenig, Andreas Dengel, Knut Hinkelmann, Koichi Kise, Robert J Howlett, Lakhmi C Jain
Place of PublicationGermany
PublisherSpringer
Pages436-445
Number of pages10
Volume6881
ISBN (Print)9783642238505
DOIs
Publication statusPublished - 2011
EventKnowledge-Based and Intelligent Information and Engineering Systems - Kaiserslautern, Kaiserslautern, Germany
Duration: 12 Sept 201114 Sept 2011

Conference

ConferenceKnowledge-Based and Intelligent Information and Engineering Systems
Abbreviated titleKES 2011
Country/TerritoryGermany
CityKaiserslautern
Period12/09/1114/09/11

Fingerprint

Dive into the research topics of 'Novel Metrics for Face Recognition Using Local Binary Patterns'. Together they form a unique fingerprint.

Cite this