Relation Learning- A New Approach to Face Recognition

Dat Tran; Xu Huang; Girija Chetty

doi:10.1007/978-3-642-23687-7_51

Relation Learning- A New Approach to Face Recognition

Dat Tran, Xu Huang, Girija Chetty

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

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 language	English
Title of host publication	International Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011)
Subtitle of host publication	Lecture Notes in Computer Science
Place of Publication	Belgium
Publisher	Springer
Pages	566-575
Number of pages	10
Volume	6915
ISBN (Electronic)	9783642236877
ISBN (Print)	9783642236860
DOIs	https://doi.org/10.1007/978-3-642-23687-7_51
Publication status	Published - 2011
Event	13th International Conference, ACIVS 2011: Advances Concepts for Intelligent Vision System - Ghent, Ghent, Belgium Duration: 22 Aug 2011 → 25 Nov 2011

Conference

Conference	13th International Conference, ACIVS 2011
Country/Territory	Belgium
City	Ghent
Period	22/08/11 → 25/11/11

Access to Document

10.1007/978-3-642-23687-7_51

Cite this

@inproceedings{27ed34123e7940c0afaac74d7b64605a,

title = "Relation Learning- A New Approach to Face Recognition",

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.",

keywords = "Face Identification, Similarity Score, Relation Learning, Support Vectore Machine",

author = "Dat Tran and Xu Huang and Girija Chetty",

year = "2011",

doi = "10.1007/978-3-642-23687-7_51",

language = "English",

isbn = "9783642236860",

volume = "6915",

pages = "566--575",

booktitle = "International Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011)",

publisher = "Springer",

address = "Netherlands",

note = "13th International Conference, ACIVS 2011 : Advances Concepts for Intelligent Vision System ; Conference date: 22-08-2011 Through 25-11-2011",

}

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, Springer, Belgium, pp. 566-575, 13th International Conference, ACIVS 2011, Ghent, Belgium, 22/08/11. https://doi.org/10.1007/978-3-642-23687-7_51

Relation Learning- A New Approach to Face Recognition. / Tran, Dat ; Huang, Xu ; Chetty, Girija.
International Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011): Lecture Notes in Computer Science. Vol. 6915 Belgium: Springer, 2011. p. 566-575.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Relation Learning- A New Approach to Face Recognition

AU - Tran, Dat

AU - Huang, Xu

AU - Chetty, Girija

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

KW - Face Identification

KW - Similarity Score

KW - Relation Learning

KW - Support Vectore Machine

U2 - 10.1007/978-3-642-23687-7_51

DO - 10.1007/978-3-642-23687-7_51

M3 - Conference contribution

SN - 9783642236860

VL - 6915

SP - 566

EP - 575

BT - International Conference on Advanced Concepts for Intelligent Vision System (ACIVS 2011)

PB - Springer

CY - Belgium

T2 - 13th International Conference, ACIVS 2011

Y2 - 22 August 2011 through 25 November 2011

ER -

Relation Learning- A New Approach to Face Recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this