Computationally efficient statistical face model in the feature space

Mohammad Haghighat; Mohamed Abdel-Mottaleb; Wadee Alhalabi

doi:10.1109/CIBIM.2014.7015453

Computationally efficient statistical face model in the feature space

Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In this paper, we present a computationally efficient statistical face modeling approach. The efficiency of our proposed approach is the result of mathematical simplifications in the core formula of a previous face modeling method and the use of the singular value decomposition. In order to reduce the errors in our resulting models, we preprocess the facial images to normalize for pose and illumination and remove little occlusions. Then, the statistical face models for the enrolled subjects are obtained from the normalized face images. The effects of the variations in pose, facial expression, and illumination on the accuracy of the system are studied. Experimental results demonstrate the reduction in the computational complexity of the new approach and its efficacy in modeling the face images.

Original language	English (US)
Title of host publication	IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM
Publisher	IEEE Computer Society
Pages	126-131
Number of pages	6
Volume	2015-January
Edition	January
DOIs	https://doi.org/10.1109/CIBIM.2014.7015453
State	Published - Jan 19 2015
Event	2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014 - Orlando, United States Duration: Dec 9 2014 → Dec 12 2014

Other

Other	2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014
Country	United States
City	Orlando
Period	12/9/14 → 12/12/14

Fingerprint

ASJC Scopus subject areas

Biotechnology
Artificial Intelligence
Computational Theory and Mathematics

Cite this

Haghighat, M., Abdel-Mottaleb, M., & Alhalabi, W. (2015). Computationally efficient statistical face model in the feature space. In IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM (January ed., Vol. 2015-January, pp. 126-131). [7015453] IEEE Computer Society. https://doi.org/10.1109/CIBIM.2014.7015453

Computationally efficient statistical face model in the feature space. / Haghighat, Mohammad; Abdel-Mottaleb, Mohamed; Alhalabi, Wadee.

IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM. Vol. 2015-January January. ed. IEEE Computer Society, 2015. p. 126-131 7015453.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Haghighat, M, Abdel-Mottaleb, M & Alhalabi, W 2015, Computationally efficient statistical face model in the feature space. in IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM. January edn, vol. 2015-January, 7015453, IEEE Computer Society, pp. 126-131, 2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014, Orlando, United States, 12/9/14. https://doi.org/10.1109/CIBIM.2014.7015453

@inproceedings{4d0b0a7e47af4d438e661099a6d655ca,

title = "Computationally efficient statistical face model in the feature space",

abstract = "In this paper, we present a computationally efficient statistical face modeling approach. The efficiency of our proposed approach is the result of mathematical simplifications in the core formula of a previous face modeling method and the use of the singular value decomposition. In order to reduce the errors in our resulting models, we preprocess the facial images to normalize for pose and illumination and remove little occlusions. Then, the statistical face models for the enrolled subjects are obtained from the normalized face images. The effects of the variations in pose, facial expression, and illumination on the accuracy of the system are studied. Experimental results demonstrate the reduction in the computational complexity of the new approach and its efficacy in modeling the face images.",

author = "Mohammad Haghighat and Mohamed Abdel-Mottaleb and Wadee Alhalabi",

year = "2015",

month = jan

day = "19",

doi = "10.1109/CIBIM.2014.7015453",

language = "English (US)",

volume = "2015-January",

pages = "126--131",

booktitle = "IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM",

publisher = "IEEE Computer Society",

edition = "January",

note = "2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014 ; Conference date: 09-12-2014 Through 12-12-2014",

}

TY - GEN

T1 - Computationally efficient statistical face model in the feature space

AU - Haghighat, Mohammad

AU - Abdel-Mottaleb, Mohamed

AU - Alhalabi, Wadee

PY - 2015/1/19

Y1 - 2015/1/19

N2 - In this paper, we present a computationally efficient statistical face modeling approach. The efficiency of our proposed approach is the result of mathematical simplifications in the core formula of a previous face modeling method and the use of the singular value decomposition. In order to reduce the errors in our resulting models, we preprocess the facial images to normalize for pose and illumination and remove little occlusions. Then, the statistical face models for the enrolled subjects are obtained from the normalized face images. The effects of the variations in pose, facial expression, and illumination on the accuracy of the system are studied. Experimental results demonstrate the reduction in the computational complexity of the new approach and its efficacy in modeling the face images.

AB - In this paper, we present a computationally efficient statistical face modeling approach. The efficiency of our proposed approach is the result of mathematical simplifications in the core formula of a previous face modeling method and the use of the singular value decomposition. In order to reduce the errors in our resulting models, we preprocess the facial images to normalize for pose and illumination and remove little occlusions. Then, the statistical face models for the enrolled subjects are obtained from the normalized face images. The effects of the variations in pose, facial expression, and illumination on the accuracy of the system are studied. Experimental results demonstrate the reduction in the computational complexity of the new approach and its efficacy in modeling the face images.

UR - http://www.scopus.com/inward/record.url?scp=84937924440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937924440&partnerID=8YFLogxK

U2 - 10.1109/CIBIM.2014.7015453

DO - 10.1109/CIBIM.2014.7015453

M3 - Conference contribution

AN - SCOPUS:84937924440

VL - 2015-January

SP - 126

EP - 131

BT - IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, CIBIM

PB - IEEE Computer Society

T2 - 2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014

Y2 - 9 December 2014 through 12 December 2014

ER -

Access to Document

10.1109/CIBIM.2014.7015453