Clustering techniques for human posture recognition: K-Means, FCM and SOM

An automated surveillance system should have the ability to recognize human behaviour and to warn security personnel of any impending suspicious activity. Human posture is one of the key aspects of analyzing human behaviour. We investigated three clustering techniques to recognize human posture. The...

Full description

Bibliographic Details
Main Authors:	Kiran, Maleeha, Lai, Weng Kin, Kyaw Kyaw, Hitke Ali
Format:	Conference or Workshop Item
Language:	English
Published:	2009
Subjects:	TK7885 Computer engineering
Online Access:	http://irep.iium.edu.my/1337/ http://irep.iium.edu.my/1337/1/Clustering_Techniques_for_Human_Posture_Recognition-K-Means%2C_FCM_and_SOM.pdf

id	iium-1337
recordtype	eprints
spelling	iium-13372011-12-20T00:11:42Z http://irep.iium.edu.my/1337/ Clustering techniques for human posture recognition: K-Means, FCM and SOM Kiran, Maleeha Lai, Weng Kin Kyaw Kyaw, Hitke Ali TK7885 Computer engineering An automated surveillance system should have the ability to recognize human behaviour and to warn security personnel of any impending suspicious activity. Human posture is one of the key aspects of analyzing human behaviour. We investigated three clustering techniques to recognize human posture. The system is first trained to recognize a pair of posture and this is repeated for three pairs of human posture. Finally the system is trained to recognize five postures together. The clustering techniques used for the purpose of our investigation included K-Means, fuzzy C-Means and Self-Organizing Maps. The results showed that K-Means and Fuzzy C-Means performed well for the three pair of posture data. However these clustering techniques gave low accuracy when we scale up the dataset to five different postures. Self- Organizing Maps produce better recognition accuracy when tested for five postures. 2009 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/1337/1/Clustering_Techniques_for_Human_Posture_Recognition-K-Means%2C_FCM_and_SOM.pdf Kiran, Maleeha and Lai, Weng Kin and Kyaw Kyaw, Hitke Ali (2009) Clustering techniques for human posture recognition: K-Means, FCM and SOM. In: 9th WSEAS international conference on signal, speech and image processing, and 9th WSEAS international conference on Multimedia, internet & video technologies, 3 - 5 September, 2009, Budapest Tech, Hungary.
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	TK7885 Computer engineering
spellingShingle	TK7885 Computer engineering Kiran, Maleeha Lai, Weng Kin Kyaw Kyaw, Hitke Ali Clustering techniques for human posture recognition: K-Means, FCM and SOM
description	An automated surveillance system should have the ability to recognize human behaviour and to warn security personnel of any impending suspicious activity. Human posture is one of the key aspects of analyzing human behaviour. We investigated three clustering techniques to recognize human posture. The system is first trained to recognize a pair of posture and this is repeated for three pairs of human posture. Finally the system is trained to recognize five postures together. The clustering techniques used for the purpose of our investigation included K-Means, fuzzy C-Means and Self-Organizing Maps. The results showed that K-Means and Fuzzy C-Means performed well for the three pair of posture data. However these clustering techniques gave low accuracy when we scale up the dataset to five different postures. Self- Organizing Maps produce better recognition accuracy when tested for five postures.
format	Conference or Workshop Item
author	Kiran, Maleeha Lai, Weng Kin Kyaw Kyaw, Hitke Ali
author_facet	Kiran, Maleeha Lai, Weng Kin Kyaw Kyaw, Hitke Ali
author_sort	Kiran, Maleeha
title	Clustering techniques for human posture recognition: K-Means, FCM and SOM
title_short	Clustering techniques for human posture recognition: K-Means, FCM and SOM
title_full	Clustering techniques for human posture recognition: K-Means, FCM and SOM
title_fullStr	Clustering techniques for human posture recognition: K-Means, FCM and SOM
title_full_unstemmed	Clustering techniques for human posture recognition: K-Means, FCM and SOM
title_sort	clustering techniques for human posture recognition: k-means, fcm and som
publishDate	2009
url	http://irep.iium.edu.my/1337/ http://irep.iium.edu.my/1337/1/Clustering_Techniques_for_Human_Posture_Recognition-K-Means%2C_FCM_and_SOM.pdf
first_indexed	2023-09-18T20:08:36Z
last_indexed	2023-09-18T20:08:36Z
_version_	1777407326331863040

Clustering techniques for human posture recognition: K-Means, FCM and SOM

Similar Items