Relation Learning- A New Approach to Face Recognition

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

Most of current machine learning methods used in face recognition systems require sufficient data to build a face model or face data description. However insufficient data is currently a common issue. This paper presents a new learning approach to tackle this issue. The proposed learning method employs not only the data in facial images but also relations between them to build relational face models. Preliminary experiments performed on the AT&T and FERET face corpus show a significant improvement for face recognition rate when only a small facial data set is available for training.
Original languageEnglish
Title of host publicationInternational Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011)
Subtitle of host publicationLecture Notes in Computer Science
Place of PublicationBelgium
PublisherSpringer
Pages566-575
Number of pages10
Volume6915
ISBN (Electronic)9783642236877
ISBN (Print)9783642236860
DOIs
Publication statusPublished - 2011
Event13th International Conference, ACIVS 2011: Advances Concepts for Intelligent Vision System - Ghent, Ghent, Belgium
Duration: 22 Aug 201125 Nov 2011

Conference

Conference13th International Conference, ACIVS 2011
CountryBelgium
CityGhent
Period22/08/1125/11/11

    Fingerprint

Cite this

Tran, D., Huang, X., & Chetty, G. (2011). Relation Learning- A New Approach to Face Recognition. In International Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011): Lecture Notes in Computer Science (Vol. 6915, pp. 566-575). Belgium: Springer. https://doi.org/10.1007/978-3-642-23687-7_51