Support vector machines for face recognition

K. S. Hareesha, Suryakanth V. Gangashetty, V. Ramaswamy

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

Abstract

Face recognition is one of the challenging problems in human-computer interaction. An automated face recognition system requires an efficient method for detection of face region in the image sequence, extraction of facial features, and construction of a recognition model. In recent years, support vector machines (SVMs) have demonstrated excellent performance in a variety of pattern recognition problems. In this paper, we apply SVMs for face recognition (recognition model). Multi-class recognition system using SVMs are built using onc-against-the-rest approach. In this approach, one SVM model is built for each persons face (class). For each SVM model an optimal hyperplane is constructed in the kernel feature space to separate the examples of a class from the examples of all the other classes. SVMs learn the boundary regions between patterns of two classes by mapping the patterns into a higher dimensional space, and seeking a separating hyperplane, so as to maximize its distance from the closest training examples. SVM based approach for face recognition has been demonstrated for partial CMU face data base. The face recognition system is evaluated on faces of 10 different persons. For each person there arc 75 faces. The results of our studies show that, the system gives about 100% detection rate.

Original languageEnglish
Title of host publicationProceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005
Pages570-575
Number of pages6
Publication statusPublished - 2005
Event2nd Indian International Conference on Artificial Intelligence, IICAI 2005 - Pune, India
Duration: 20-12-200522-12-2005

Conference

Conference2nd Indian International Conference on Artificial Intelligence, IICAI 2005
CountryIndia
CityPune
Period20-12-0522-12-05

Fingerprint

Face recognition
Support vector machines
Human computer interaction
Pattern recognition

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Hareesha, K. S., Gangashetty, S. V., & Ramaswamy, V. (2005). Support vector machines for face recognition. In Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005 (pp. 570-575)
Hareesha, K. S. ; Gangashetty, Suryakanth V. ; Ramaswamy, V. / Support vector machines for face recognition. Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005. 2005. pp. 570-575
@inproceedings{200960f36ccd4a3c823668c070b67cf9,
title = "Support vector machines for face recognition",
abstract = "Face recognition is one of the challenging problems in human-computer interaction. An automated face recognition system requires an efficient method for detection of face region in the image sequence, extraction of facial features, and construction of a recognition model. In recent years, support vector machines (SVMs) have demonstrated excellent performance in a variety of pattern recognition problems. In this paper, we apply SVMs for face recognition (recognition model). Multi-class recognition system using SVMs are built using onc-against-the-rest approach. In this approach, one SVM model is built for each persons face (class). For each SVM model an optimal hyperplane is constructed in the kernel feature space to separate the examples of a class from the examples of all the other classes. SVMs learn the boundary regions between patterns of two classes by mapping the patterns into a higher dimensional space, and seeking a separating hyperplane, so as to maximize its distance from the closest training examples. SVM based approach for face recognition has been demonstrated for partial CMU face data base. The face recognition system is evaluated on faces of 10 different persons. For each person there arc 75 faces. The results of our studies show that, the system gives about 100{\%} detection rate.",
author = "Hareesha, {K. S.} and Gangashetty, {Suryakanth V.} and V. Ramaswamy",
year = "2005",
language = "English",
isbn = "0972741216",
pages = "570--575",
booktitle = "Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005",

}

Hareesha, KS, Gangashetty, SV & Ramaswamy, V 2005, Support vector machines for face recognition. in Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005. pp. 570-575, 2nd Indian International Conference on Artificial Intelligence, IICAI 2005, Pune, India, 20-12-05.

Support vector machines for face recognition. / Hareesha, K. S.; Gangashetty, Suryakanth V.; Ramaswamy, V.

Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005. 2005. p. 570-575.

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

TY - GEN

T1 - Support vector machines for face recognition

AU - Hareesha, K. S.

AU - Gangashetty, Suryakanth V.

AU - Ramaswamy, V.

PY - 2005

Y1 - 2005

N2 - Face recognition is one of the challenging problems in human-computer interaction. An automated face recognition system requires an efficient method for detection of face region in the image sequence, extraction of facial features, and construction of a recognition model. In recent years, support vector machines (SVMs) have demonstrated excellent performance in a variety of pattern recognition problems. In this paper, we apply SVMs for face recognition (recognition model). Multi-class recognition system using SVMs are built using onc-against-the-rest approach. In this approach, one SVM model is built for each persons face (class). For each SVM model an optimal hyperplane is constructed in the kernel feature space to separate the examples of a class from the examples of all the other classes. SVMs learn the boundary regions between patterns of two classes by mapping the patterns into a higher dimensional space, and seeking a separating hyperplane, so as to maximize its distance from the closest training examples. SVM based approach for face recognition has been demonstrated for partial CMU face data base. The face recognition system is evaluated on faces of 10 different persons. For each person there arc 75 faces. The results of our studies show that, the system gives about 100% detection rate.

AB - Face recognition is one of the challenging problems in human-computer interaction. An automated face recognition system requires an efficient method for detection of face region in the image sequence, extraction of facial features, and construction of a recognition model. In recent years, support vector machines (SVMs) have demonstrated excellent performance in a variety of pattern recognition problems. In this paper, we apply SVMs for face recognition (recognition model). Multi-class recognition system using SVMs are built using onc-against-the-rest approach. In this approach, one SVM model is built for each persons face (class). For each SVM model an optimal hyperplane is constructed in the kernel feature space to separate the examples of a class from the examples of all the other classes. SVMs learn the boundary regions between patterns of two classes by mapping the patterns into a higher dimensional space, and seeking a separating hyperplane, so as to maximize its distance from the closest training examples. SVM based approach for face recognition has been demonstrated for partial CMU face data base. The face recognition system is evaluated on faces of 10 different persons. For each person there arc 75 faces. The results of our studies show that, the system gives about 100% detection rate.

UR - http://www.scopus.com/inward/record.url?scp=84872076115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872076115&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0972741216

SN - 9780972741217

SP - 570

EP - 575

BT - Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005

ER -

Hareesha KS, Gangashetty SV, Ramaswamy V. Support vector machines for face recognition. In Proceedings of the 2nd Indian International Conference on Artificial Intelligence, IICAI 2005. 2005. p. 570-575