Joint weighted dictionary learning and classifier training for robust biometric recognition

Rahman Khorsandi, Ali Taalimi, Mohamed Abdel-Mottaleb, Hairong Qi

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

2 Citations (Scopus)

Abstract

In this paper, we present an automated system for robust biometric recognition based upon sparse representation and dictionary learning. In sparse representation, extracted features from the training data are used to develop a dictionary. Training data of real world applications are likely to be exposed to geometric transformations, which is a big challenge for designing of discriminative dictionaries. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. We propose joint weighted dictionary learning and classifier training (JWDL-CT) approach which simultaneously learns from a set of training samples along with weight vectors that correspond to the atoms in the learnt dictionary. The components of the weight vector associated with an atom represent the relationship between the atom and each of the classes. The weight vectors and atoms are jointly obtained during the dictionary learning. In the proposed method, a constraint is imposed on the correlation between the atoms to decrease the similarity between these atoms. The proposed dictionary learning objective function enhances the class-discrimination capabilities of individual atoms that renders the designed dictionaries especially suitable for classification of query images with very sparse representation. Experiments conducted on the West Virginia University (WVU) and the University of Notre Dame (UND) datasets for ear recognition show that the proposed method outperforms other state-of-the-art classifiers.

Original languageEnglish (US)
Title of host publication2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1307-1311
Number of pages5
ISBN (Print)9781479975914
DOIs
StatePublished - Feb 23 2016
EventIEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 - Orlando, United States
Duration: Dec 13 2015Dec 16 2015

Other

OtherIEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
CountryUnited States
CityOrlando
Period12/13/1512/16/15

Fingerprint

Biometrics
Glossaries
Classifiers
Atoms

Keywords

  • Biometrics
  • Classification
  • Dictionary Learning
  • Sparse Representation

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Khorsandi, R., Taalimi, A., Abdel-Mottaleb, M., & Qi, H. (2016). Joint weighted dictionary learning and classifier training for robust biometric recognition. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 (pp. 1307-1311). [7418410] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2015.7418410

Joint weighted dictionary learning and classifier training for robust biometric recognition. / Khorsandi, Rahman; Taalimi, Ali; Abdel-Mottaleb, Mohamed; Qi, Hairong.

2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1307-1311 7418410.

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

Khorsandi, R, Taalimi, A, Abdel-Mottaleb, M & Qi, H 2016, Joint weighted dictionary learning and classifier training for robust biometric recognition. in 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015., 7418410, Institute of Electrical and Electronics Engineers Inc., pp. 1307-1311, IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Orlando, United States, 12/13/15. https://doi.org/10.1109/GlobalSIP.2015.7418410
Khorsandi R, Taalimi A, Abdel-Mottaleb M, Qi H. Joint weighted dictionary learning and classifier training for robust biometric recognition. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1307-1311. 7418410 https://doi.org/10.1109/GlobalSIP.2015.7418410
Khorsandi, Rahman ; Taalimi, Ali ; Abdel-Mottaleb, Mohamed ; Qi, Hairong. / Joint weighted dictionary learning and classifier training for robust biometric recognition. 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1307-1311
@inproceedings{92eaea8940b54e1a8512b4d57a5ceb29,
title = "Joint weighted dictionary learning and classifier training for robust biometric recognition",
abstract = "In this paper, we present an automated system for robust biometric recognition based upon sparse representation and dictionary learning. In sparse representation, extracted features from the training data are used to develop a dictionary. Training data of real world applications are likely to be exposed to geometric transformations, which is a big challenge for designing of discriminative dictionaries. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. We propose joint weighted dictionary learning and classifier training (JWDL-CT) approach which simultaneously learns from a set of training samples along with weight vectors that correspond to the atoms in the learnt dictionary. The components of the weight vector associated with an atom represent the relationship between the atom and each of the classes. The weight vectors and atoms are jointly obtained during the dictionary learning. In the proposed method, a constraint is imposed on the correlation between the atoms to decrease the similarity between these atoms. The proposed dictionary learning objective function enhances the class-discrimination capabilities of individual atoms that renders the designed dictionaries especially suitable for classification of query images with very sparse representation. Experiments conducted on the West Virginia University (WVU) and the University of Notre Dame (UND) datasets for ear recognition show that the proposed method outperforms other state-of-the-art classifiers.",
keywords = "Biometrics, Classification, Dictionary Learning, Sparse Representation",
author = "Rahman Khorsandi and Ali Taalimi and Mohamed Abdel-Mottaleb and Hairong Qi",
year = "2016",
month = "2",
day = "23",
doi = "10.1109/GlobalSIP.2015.7418410",
language = "English (US)",
isbn = "9781479975914",
pages = "1307--1311",
booktitle = "2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Joint weighted dictionary learning and classifier training for robust biometric recognition

AU - Khorsandi, Rahman

AU - Taalimi, Ali

AU - Abdel-Mottaleb, Mohamed

AU - Qi, Hairong

PY - 2016/2/23

Y1 - 2016/2/23

N2 - In this paper, we present an automated system for robust biometric recognition based upon sparse representation and dictionary learning. In sparse representation, extracted features from the training data are used to develop a dictionary. Training data of real world applications are likely to be exposed to geometric transformations, which is a big challenge for designing of discriminative dictionaries. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. We propose joint weighted dictionary learning and classifier training (JWDL-CT) approach which simultaneously learns from a set of training samples along with weight vectors that correspond to the atoms in the learnt dictionary. The components of the weight vector associated with an atom represent the relationship between the atom and each of the classes. The weight vectors and atoms are jointly obtained during the dictionary learning. In the proposed method, a constraint is imposed on the correlation between the atoms to decrease the similarity between these atoms. The proposed dictionary learning objective function enhances the class-discrimination capabilities of individual atoms that renders the designed dictionaries especially suitable for classification of query images with very sparse representation. Experiments conducted on the West Virginia University (WVU) and the University of Notre Dame (UND) datasets for ear recognition show that the proposed method outperforms other state-of-the-art classifiers.

AB - In this paper, we present an automated system for robust biometric recognition based upon sparse representation and dictionary learning. In sparse representation, extracted features from the training data are used to develop a dictionary. Training data of real world applications are likely to be exposed to geometric transformations, which is a big challenge for designing of discriminative dictionaries. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. We propose joint weighted dictionary learning and classifier training (JWDL-CT) approach which simultaneously learns from a set of training samples along with weight vectors that correspond to the atoms in the learnt dictionary. The components of the weight vector associated with an atom represent the relationship between the atom and each of the classes. The weight vectors and atoms are jointly obtained during the dictionary learning. In the proposed method, a constraint is imposed on the correlation between the atoms to decrease the similarity between these atoms. The proposed dictionary learning objective function enhances the class-discrimination capabilities of individual atoms that renders the designed dictionaries especially suitable for classification of query images with very sparse representation. Experiments conducted on the West Virginia University (WVU) and the University of Notre Dame (UND) datasets for ear recognition show that the proposed method outperforms other state-of-the-art classifiers.

KW - Biometrics

KW - Classification

KW - Dictionary Learning

KW - Sparse Representation

UR - http://www.scopus.com/inward/record.url?scp=84964788384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964788384&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2015.7418410

DO - 10.1109/GlobalSIP.2015.7418410

M3 - Conference contribution

SN - 9781479975914

SP - 1307

EP - 1311

BT - 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -