Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm

Rahman Khorsandi, Ali Taalimi, Mohamed Abdel-Mottaleb

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. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. Dictionary learning for sparse representation has shown to improve the results in classification and recognition tasks since class labels can be used in obtaining the atoms of learnt dictionary. We propose a joint weighted dictionary learning which simultaneously learns from a set of training samples an over complete dictionary 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 obtained atoms that represent different classes to decrease the similarity between these atoms. In addition, we use smoothed L0 norm which is a fast algorithm to find the sparsest solution. 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 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479987764
DOIs
StatePublished - Dec 16 2015
Event7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015 - Arlington, United States
Duration: Sep 8 2015Sep 11 2015

Other

Other7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
CountryUnited States
CityArlington
Period9/8/159/11/15

Fingerprint

Biometrics
Glossaries
Norm
Atoms
Sparse Representation
Dictionary
Learning
Training Samples
Fast Algorithm
Linear Combination
Labels
Classifiers
Classifier
Decrease

ASJC Scopus subject areas

  • Statistics and Probability
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Khorsandi, R., Taalimi, A., & Abdel-Mottaleb, M. (2015). Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015 [7358792] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BTAS.2015.7358792

Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm. / Khorsandi, Rahman; Taalimi, Ali; Abdel-Mottaleb, Mohamed.

2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7358792.

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

Khorsandi, R, Taalimi, A & Abdel-Mottaleb, M 2015, Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm. in 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015., 7358792, Institute of Electrical and Electronics Engineers Inc., 7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015, Arlington, United States, 9/8/15. https://doi.org/10.1109/BTAS.2015.7358792
Khorsandi R, Taalimi A, Abdel-Mottaleb M. Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7358792 https://doi.org/10.1109/BTAS.2015.7358792
Khorsandi, Rahman ; Taalimi, Ali ; Abdel-Mottaleb, Mohamed. / Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm. 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{d0ef462f0dc04825b58a38b0a5f0eca7,
title = "Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm",
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. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. Dictionary learning for sparse representation has shown to improve the results in classification and recognition tasks since class labels can be used in obtaining the atoms of learnt dictionary. We propose a joint weighted dictionary learning which simultaneously learns from a set of training samples an over complete dictionary 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 obtained atoms that represent different classes to decrease the similarity between these atoms. In addition, we use smoothed L0 norm which is a fast algorithm to find the sparsest solution. 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.",
author = "Rahman Khorsandi and Ali Taalimi and Mohamed Abdel-Mottaleb",
year = "2015",
month = "12",
day = "16",
doi = "10.1109/BTAS.2015.7358792",
language = "English (US)",
isbn = "9781479987764",
booktitle = "2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robust biometrics recognition using joint weighted dictionary learning and smoothed L0 norm

AU - Khorsandi, Rahman

AU - Taalimi, Ali

AU - Abdel-Mottaleb, Mohamed

PY - 2015/12/16

Y1 - 2015/12/16

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. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. Dictionary learning for sparse representation has shown to improve the results in classification and recognition tasks since class labels can be used in obtaining the atoms of learnt dictionary. We propose a joint weighted dictionary learning which simultaneously learns from a set of training samples an over complete dictionary 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 obtained atoms that represent different classes to decrease the similarity between these atoms. In addition, we use smoothed L0 norm which is a fast algorithm to find the sparsest solution. 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. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. Dictionary learning for sparse representation has shown to improve the results in classification and recognition tasks since class labels can be used in obtaining the atoms of learnt dictionary. We propose a joint weighted dictionary learning which simultaneously learns from a set of training samples an over complete dictionary 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 obtained atoms that represent different classes to decrease the similarity between these atoms. In addition, we use smoothed L0 norm which is a fast algorithm to find the sparsest solution. 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.

UR - http://www.scopus.com/inward/record.url?scp=84962860396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962860396&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2015.7358792

DO - 10.1109/BTAS.2015.7358792

M3 - Conference contribution

SN - 9781479987764

BT - 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -