Face identification using large feature sets

William Robson Schwartz; Huimin Guo; Jonghyun Choi; Larry S. Davis

doi:10.1109/TIP.2011.2176951

Face identification using large feature sets

William Robson Schwartz, Huimin Guo, Jonghyun Choi, Larry S. Davis

Department of Artificial Intelligence

Research output: Contribution to journal › Article › peer-review

71 Citations (Scopus)

Abstract

With the goal of matching unknown faces against a gallery of known people, the face identification task has been studied for several decades. There are very accurate techniques to perform face identification in controlled environments, particularly when large numbers of samples are available for each face. However, face identification under uncontrolled environments or with a lack of training data is still an unsolved problem. We employ a large and rich set of feature descriptors (with more than 70000 descriptors) for face identification using partial least squares to perform multichannel feature weighting. Then, we extend the method to a tree-based discriminative structure to reduce the time required to evaluate probe samples. The method is evaluated on Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. Experiments show that our identification method outperforms current state-of-the-art results, particularly for identifying faces acquired across varying conditions.

Original language	English
Article number	6086621
Pages (from-to)	2245-2255
Number of pages	11
Journal	IEEE Transactions on Image Processing
Volume	21
Issue number	4
DOIs	https://doi.org/10.1109/TIP.2011.2176951
Publication status	Published - 2012 Apr

Bibliographical note

Funding Information:
Manuscript received February 21, 2011; revised June 22, 2011; accepted October 29, 2011. Date of publication November 22, 2011; date of current version March 21, 2012. This work was supported in part by Intelligence Advanced Research Projects Activity funded by the Office of the Director of National Intelligence through the Army Research Laboratory and in part by Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) under Grant 2010/10618-3. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Alex ChiChung Kot.

All Science Journal Classification (ASJC) codes

Software
Computer Graphics and Computer-Aided Design

Access to Document

10.1109/TIP.2011.2176951

Cite this

@article{9b7b2ee03cba4a579283b557cc6734bd,

title = "Face identification using large feature sets",

abstract = "With the goal of matching unknown faces against a gallery of known people, the face identification task has been studied for several decades. There are very accurate techniques to perform face identification in controlled environments, particularly when large numbers of samples are available for each face. However, face identification under uncontrolled environments or with a lack of training data is still an unsolved problem. We employ a large and rich set of feature descriptors (with more than 70000 descriptors) for face identification using partial least squares to perform multichannel feature weighting. Then, we extend the method to a tree-based discriminative structure to reduce the time required to evaluate probe samples. The method is evaluated on Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. Experiments show that our identification method outperforms current state-of-the-art results, particularly for identifying faces acquired across varying conditions.",

author = "Schwartz, {William Robson} and Huimin Guo and Jonghyun Choi and Davis, {Larry S.}",

note = "Funding Information: Manuscript received February 21, 2011; revised June 22, 2011; accepted October 29, 2011. Date of publication November 22, 2011; date of current version March 21, 2012. This work was supported in part by Intelligence Advanced Research Projects Activity funded by the Office of the Director of National Intelligence through the Army Research Laboratory and in part by Funda{\c c}{\~a}o de Amparo {\`a} Pesquisa do Estado de S{\~a}o Paulo (FAPESP) under Grant 2010/10618-3. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Alex ChiChung Kot.",

year = "2012",

month = apr,

doi = "10.1109/TIP.2011.2176951",

language = "English",

volume = "21",

pages = "2245--2255",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Face identification using large feature sets

AU - Schwartz, William Robson

AU - Guo, Huimin

AU - Choi, Jonghyun

AU - Davis, Larry S.

N1 - Funding Information: Manuscript received February 21, 2011; revised June 22, 2011; accepted October 29, 2011. Date of publication November 22, 2011; date of current version March 21, 2012. This work was supported in part by Intelligence Advanced Research Projects Activity funded by the Office of the Director of National Intelligence through the Army Research Laboratory and in part by Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) under Grant 2010/10618-3. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Alex ChiChung Kot.

PY - 2012/4

Y1 - 2012/4

N2 - With the goal of matching unknown faces against a gallery of known people, the face identification task has been studied for several decades. There are very accurate techniques to perform face identification in controlled environments, particularly when large numbers of samples are available for each face. However, face identification under uncontrolled environments or with a lack of training data is still an unsolved problem. We employ a large and rich set of feature descriptors (with more than 70000 descriptors) for face identification using partial least squares to perform multichannel feature weighting. Then, we extend the method to a tree-based discriminative structure to reduce the time required to evaluate probe samples. The method is evaluated on Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. Experiments show that our identification method outperforms current state-of-the-art results, particularly for identifying faces acquired across varying conditions.

AB - With the goal of matching unknown faces against a gallery of known people, the face identification task has been studied for several decades. There are very accurate techniques to perform face identification in controlled environments, particularly when large numbers of samples are available for each face. However, face identification under uncontrolled environments or with a lack of training data is still an unsolved problem. We employ a large and rich set of feature descriptors (with more than 70000 descriptors) for face identification using partial least squares to perform multichannel feature weighting. Then, we extend the method to a tree-based discriminative structure to reduce the time required to evaluate probe samples. The method is evaluated on Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. Experiments show that our identification method outperforms current state-of-the-art results, particularly for identifying faces acquired across varying conditions.

UR - http://www.scopus.com/inward/record.url?scp=84859067740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859067740&partnerID=8YFLogxK

U2 - 10.1109/TIP.2011.2176951

DO - 10.1109/TIP.2011.2176951

M3 - Article

C2 - 22128005

AN - SCOPUS:84859067740

SN - 1057-7149

VL - 21

SP - 2245

EP - 2255

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

IS - 4

M1 - 6086621

ER -

Face identification using large feature sets

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this