Discriminant Tchebichef based moment features for face recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Face representation using small number of features with highest discriminatory measure is vital in the development of a face recognition system. In the holistic based approach, features are extracted from the global appearance of a face. Fisher's Linear Discriminant Analysis (FLD) is a popular holistic based feature extractor. However, it is subject to several limitations such as small sample size problem and heavy computation due to large scatter matrix. In this paper, a new approach is introduced to remedy this problem. Firstly, discrete orthogonal Tchebichef moments are computed to summarise the information lying in a large sized facial image. Secondly, the scatter matrices are calculated on the Tchebichef moments to obtain an optimised discriminant feature using FLD. The proposed method is tested on ORL database, which consist of 40 subjects with 400 images. Highest recognition rate of 96.5% were obtained using only 29 features.

Original languageEnglish
Title of host publication2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011
Pages192-197
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011 - Kuala Lumpur, Malaysia
Duration: 16 Nov 201118 Nov 2011

Other

Other2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011
CountryMalaysia
CityKuala Lumpur
Period16/11/1118/11/11

Fingerprint

Discriminant analysis
Face recognition

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

V. Janahiraman, T., Omar, J., & Farrukh, H. N. (2011). Discriminant Tchebichef based moment features for face recognition. In 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011 (pp. 192-197). [6144081] https://doi.org/10.1109/ICSIPA.2011.6144081
V. Janahiraman, Tiagrajah ; Omar, Jamaludin ; Farrukh, H. N. / Discriminant Tchebichef based moment features for face recognition. 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. pp. 192-197
@inproceedings{90d2ada09a374a99a955af1f50c7aa65,
title = "Discriminant Tchebichef based moment features for face recognition",
abstract = "Face representation using small number of features with highest discriminatory measure is vital in the development of a face recognition system. In the holistic based approach, features are extracted from the global appearance of a face. Fisher's Linear Discriminant Analysis (FLD) is a popular holistic based feature extractor. However, it is subject to several limitations such as small sample size problem and heavy computation due to large scatter matrix. In this paper, a new approach is introduced to remedy this problem. Firstly, discrete orthogonal Tchebichef moments are computed to summarise the information lying in a large sized facial image. Secondly, the scatter matrices are calculated on the Tchebichef moments to obtain an optimised discriminant feature using FLD. The proposed method is tested on ORL database, which consist of 40 subjects with 400 images. Highest recognition rate of 96.5{\%} were obtained using only 29 features.",
author = "{V. Janahiraman}, Tiagrajah and Jamaludin Omar and Farrukh, {H. N.}",
year = "2011",
doi = "10.1109/ICSIPA.2011.6144081",
language = "English",
isbn = "9781457702419",
pages = "192--197",
booktitle = "2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011",

}

V. Janahiraman, T, Omar, J & Farrukh, HN 2011, Discriminant Tchebichef based moment features for face recognition. in 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011., 6144081, pp. 192-197, 2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011, Kuala Lumpur, Malaysia, 16/11/11. https://doi.org/10.1109/ICSIPA.2011.6144081

Discriminant Tchebichef based moment features for face recognition. / V. Janahiraman, Tiagrajah; Omar, Jamaludin; Farrukh, H. N.

2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. p. 192-197 6144081.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Discriminant Tchebichef based moment features for face recognition

AU - V. Janahiraman, Tiagrajah

AU - Omar, Jamaludin

AU - Farrukh, H. N.

PY - 2011

Y1 - 2011

N2 - Face representation using small number of features with highest discriminatory measure is vital in the development of a face recognition system. In the holistic based approach, features are extracted from the global appearance of a face. Fisher's Linear Discriminant Analysis (FLD) is a popular holistic based feature extractor. However, it is subject to several limitations such as small sample size problem and heavy computation due to large scatter matrix. In this paper, a new approach is introduced to remedy this problem. Firstly, discrete orthogonal Tchebichef moments are computed to summarise the information lying in a large sized facial image. Secondly, the scatter matrices are calculated on the Tchebichef moments to obtain an optimised discriminant feature using FLD. The proposed method is tested on ORL database, which consist of 40 subjects with 400 images. Highest recognition rate of 96.5% were obtained using only 29 features.

AB - Face representation using small number of features with highest discriminatory measure is vital in the development of a face recognition system. In the holistic based approach, features are extracted from the global appearance of a face. Fisher's Linear Discriminant Analysis (FLD) is a popular holistic based feature extractor. However, it is subject to several limitations such as small sample size problem and heavy computation due to large scatter matrix. In this paper, a new approach is introduced to remedy this problem. Firstly, discrete orthogonal Tchebichef moments are computed to summarise the information lying in a large sized facial image. Secondly, the scatter matrices are calculated on the Tchebichef moments to obtain an optimised discriminant feature using FLD. The proposed method is tested on ORL database, which consist of 40 subjects with 400 images. Highest recognition rate of 96.5% were obtained using only 29 features.

UR - http://www.scopus.com/inward/record.url?scp=84857466779&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857466779&partnerID=8YFLogxK

U2 - 10.1109/ICSIPA.2011.6144081

DO - 10.1109/ICSIPA.2011.6144081

M3 - Conference contribution

SN - 9781457702419

SP - 192

EP - 197

BT - 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011

ER -

V. Janahiraman T, Omar J, Farrukh HN. Discriminant Tchebichef based moment features for face recognition. In 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. p. 192-197. 6144081 https://doi.org/10.1109/ICSIPA.2011.6144081