Efficient multi-algorithmic approaches for face recognition using subspace methods

Mohammad Imran, S. Noushath, Abdelhamid Abdesselam, Karan Jetly, Karthikeyan

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

3 Citations (Scopus)

Abstract

Face recognition is an active research in the field of biometrics due to its potential benefits to various security based applications. To make the results of face recognition unsusceptible to different kinds of variations in the image and to enhance the accuracy, robustness of two or more methods can be fused in a single framework. The fusion can be achieved at various levels. Objective of this paper is to suggest optimal fusion of subspace methods to achieve robust results for various test conditions. This is achieved by performing feature level fusion of popular subspace methods namely PCA, LDA, LPP and ICA1. The Fusion is performed by considering different combinations of set of two, three and four subspace methods. Experiments are conducted by using two different databases: ORL and Yale. Experimental results suggest that by the fusion of these subspace approaches; there is a significant improvement in the accuracy compared to performance of an individual subspace method. This work helped us to determine the optimal combination of subspace methods to achieve robust results for specific test conditions.

Original languageEnglish
Title of host publication2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013
DOIs
Publication statusPublished - 2013
Event2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013 - Sharjah, United Arab Emirates
Duration: Feb 12 2013Feb 14 2013

Other

Other2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013
CountryUnited Arab Emirates
CitySharjah
Period2/12/132/14/13

Fingerprint

Face recognition
Fusion reactions
Biometrics
Experiments

Keywords

  • Biometrics
  • Face
  • Feature level
  • Fusion
  • subspace methods

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Imran, M., Noushath, S., Abdesselam, A., Jetly, K., & Karthikeyan (2013). Efficient multi-algorithmic approaches for face recognition using subspace methods. In 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013 [6487264] https://doi.org/10.1109/ICCSPA.2013.6487264

Efficient multi-algorithmic approaches for face recognition using subspace methods. / Imran, Mohammad; Noushath, S.; Abdesselam, Abdelhamid; Jetly, Karan; Karthikeyan.

2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013. 2013. 6487264.

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

Imran, M, Noushath, S, Abdesselam, A, Jetly, K & Karthikeyan 2013, Efficient multi-algorithmic approaches for face recognition using subspace methods. in 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013., 6487264, 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013, Sharjah, United Arab Emirates, 2/12/13. https://doi.org/10.1109/ICCSPA.2013.6487264
Imran M, Noushath S, Abdesselam A, Jetly K, Karthikeyan. Efficient multi-algorithmic approaches for face recognition using subspace methods. In 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013. 2013. 6487264 https://doi.org/10.1109/ICCSPA.2013.6487264
Imran, Mohammad ; Noushath, S. ; Abdesselam, Abdelhamid ; Jetly, Karan ; Karthikeyan. / Efficient multi-algorithmic approaches for face recognition using subspace methods. 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013. 2013.
@inproceedings{0db0dafef80a4ee78da825a42881b717,
title = "Efficient multi-algorithmic approaches for face recognition using subspace methods",
abstract = "Face recognition is an active research in the field of biometrics due to its potential benefits to various security based applications. To make the results of face recognition unsusceptible to different kinds of variations in the image and to enhance the accuracy, robustness of two or more methods can be fused in a single framework. The fusion can be achieved at various levels. Objective of this paper is to suggest optimal fusion of subspace methods to achieve robust results for various test conditions. This is achieved by performing feature level fusion of popular subspace methods namely PCA, LDA, LPP and ICA1. The Fusion is performed by considering different combinations of set of two, three and four subspace methods. Experiments are conducted by using two different databases: ORL and Yale. Experimental results suggest that by the fusion of these subspace approaches; there is a significant improvement in the accuracy compared to performance of an individual subspace method. This work helped us to determine the optimal combination of subspace methods to achieve robust results for specific test conditions.",
keywords = "Biometrics, Face, Feature level, Fusion, subspace methods",
author = "Mohammad Imran and S. Noushath and Abdelhamid Abdesselam and Karan Jetly and Karthikeyan",
year = "2013",
doi = "10.1109/ICCSPA.2013.6487264",
language = "English",
isbn = "9781467328210",
booktitle = "2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013",

}

TY - GEN

T1 - Efficient multi-algorithmic approaches for face recognition using subspace methods

AU - Imran, Mohammad

AU - Noushath, S.

AU - Abdesselam, Abdelhamid

AU - Jetly, Karan

AU - Karthikeyan,

PY - 2013

Y1 - 2013

N2 - Face recognition is an active research in the field of biometrics due to its potential benefits to various security based applications. To make the results of face recognition unsusceptible to different kinds of variations in the image and to enhance the accuracy, robustness of two or more methods can be fused in a single framework. The fusion can be achieved at various levels. Objective of this paper is to suggest optimal fusion of subspace methods to achieve robust results for various test conditions. This is achieved by performing feature level fusion of popular subspace methods namely PCA, LDA, LPP and ICA1. The Fusion is performed by considering different combinations of set of two, three and four subspace methods. Experiments are conducted by using two different databases: ORL and Yale. Experimental results suggest that by the fusion of these subspace approaches; there is a significant improvement in the accuracy compared to performance of an individual subspace method. This work helped us to determine the optimal combination of subspace methods to achieve robust results for specific test conditions.

AB - Face recognition is an active research in the field of biometrics due to its potential benefits to various security based applications. To make the results of face recognition unsusceptible to different kinds of variations in the image and to enhance the accuracy, robustness of two or more methods can be fused in a single framework. The fusion can be achieved at various levels. Objective of this paper is to suggest optimal fusion of subspace methods to achieve robust results for various test conditions. This is achieved by performing feature level fusion of popular subspace methods namely PCA, LDA, LPP and ICA1. The Fusion is performed by considering different combinations of set of two, three and four subspace methods. Experiments are conducted by using two different databases: ORL and Yale. Experimental results suggest that by the fusion of these subspace approaches; there is a significant improvement in the accuracy compared to performance of an individual subspace method. This work helped us to determine the optimal combination of subspace methods to achieve robust results for specific test conditions.

KW - Biometrics

KW - Face

KW - Feature level

KW - Fusion

KW - subspace methods

UR - http://www.scopus.com/inward/record.url?scp=84876040648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876040648&partnerID=8YFLogxK

U2 - 10.1109/ICCSPA.2013.6487264

DO - 10.1109/ICCSPA.2013.6487264

M3 - Conference contribution

SN - 9781467328210

BT - 2013 1st International Conference on Communications, Signal Processing and Their Applications, ICCSPA 2013

ER -