Approximate nearest neighbor search using self-organizing map clustering for face recognition system

© 2014 IEEE. This paper presents face recognition system that is based on Self-Organizing Map (SOM) clustering. In order to reduce the time consumption in nearest neighbor search, SOM clustering scheme is used to group the training data and determine prototypes of each group. Local feature selection...

Full description

Saved in:

Bibliographic Details
Main Authors:	Paitoon Yodkhad, Aram Kawewong, Karn Patanukhom
Format:	Conference Proceeding
Published:	2018
Subjects:	Computer Science Mathematics Medicine
Online Access:	https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988268343&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/53419
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Chiang Mai University

id	th-cmuir.6653943832-53419
record_format	dspace
spelling	th-cmuir.6653943832-534192018-09-04T09:58:11Z Approximate nearest neighbor search using self-organizing map clustering for face recognition system Paitoon Yodkhad Aram Kawewong Karn Patanukhom Computer Science Mathematics Medicine © 2014 IEEE. This paper presents face recognition system that is based on Self-Organizing Map (SOM) clustering. In order to reduce the time consumption in nearest neighbor search, SOM clustering scheme is used to group the training data and determine prototypes of each group. Local feature selection process is employed to reduce dimension of data in each group. To show the performance of the proposed scheme over various choices of feature extraction method, PCA (Eigenface), 2DPCA, and SOM-Face are tested in the experiment. Recognition accuracy and time consumption are measured in comparison with k-d Tree search and the other clustering based search schemes by using the dataset of 1,560 face images from 156 people. The experiments show that the proposed scheme can obtain the best recognition rate of 99.36% while it reduces the time consumption. 2018-09-04T09:48:56Z 2018-09-04T09:48:56Z 2014-01-01 Conference Proceeding 2-s2.0-84988268343 10.1109/ICSEC.2014.6978186 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988268343&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/53419
institution	Chiang Mai University
building	Chiang Mai University Library
country	Thailand
collection	CMU Intellectual Repository
topic	Computer Science Mathematics Medicine
spellingShingle	Computer Science Mathematics Medicine Paitoon Yodkhad Aram Kawewong Karn Patanukhom Approximate nearest neighbor search using self-organizing map clustering for face recognition system
description	© 2014 IEEE. This paper presents face recognition system that is based on Self-Organizing Map (SOM) clustering. In order to reduce the time consumption in nearest neighbor search, SOM clustering scheme is used to group the training data and determine prototypes of each group. Local feature selection process is employed to reduce dimension of data in each group. To show the performance of the proposed scheme over various choices of feature extraction method, PCA (Eigenface), 2DPCA, and SOM-Face are tested in the experiment. Recognition accuracy and time consumption are measured in comparison with k-d Tree search and the other clustering based search schemes by using the dataset of 1,560 face images from 156 people. The experiments show that the proposed scheme can obtain the best recognition rate of 99.36% while it reduces the time consumption.
format	Conference Proceeding
author	Paitoon Yodkhad Aram Kawewong Karn Patanukhom
author_facet	Paitoon Yodkhad Aram Kawewong Karn Patanukhom
author_sort	Paitoon Yodkhad
title	Approximate nearest neighbor search using self-organizing map clustering for face recognition system
title_short	Approximate nearest neighbor search using self-organizing map clustering for face recognition system
title_full	Approximate nearest neighbor search using self-organizing map clustering for face recognition system
title_fullStr	Approximate nearest neighbor search using self-organizing map clustering for face recognition system
title_full_unstemmed	Approximate nearest neighbor search using self-organizing map clustering for face recognition system
title_sort	approximate nearest neighbor search using self-organizing map clustering for face recognition system
publishDate	2018
url	https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988268343&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/53419
_version_	1681424131755606016

Approximate nearest neighbor search using self-organizing map clustering for face recognition system

Similar Items