Shock graph for representation and modeling of posture

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.

Original languageEnglish
Pages (from-to)507-515
Number of pages9
JournalETRI Journal
Volume29
Issue number4
Publication statusPublished - Aug 2007

Fingerprint

Multilayer neural networks
Decision trees
Support vector machines
Classifiers

Keywords

  • Decision tree
  • Human posture
  • Medial axis
  • Shock graph
  • Skeletonization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Cite this

Shock graph for representation and modeling of posture. / Tahir, Nooritawati Md; Hussain, Aini; Abdul Samad, Salina; Husain, Hafizah.

In: ETRI Journal, Vol. 29, No. 4, 08.2007, p. 507-515.

Research output: Contribution to journalArticle

@article{bf25e47dc42d4e949bc1872dca36f5d9,
title = "Shock graph for representation and modeling of posture",
abstract = "Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.",
keywords = "Decision tree, Human posture, Medial axis, Shock graph, Skeletonization",
author = "Tahir, {Nooritawati Md} and Aini Hussain and {Abdul Samad}, Salina and Hafizah Husain",
year = "2007",
month = "8",
language = "English",
volume = "29",
pages = "507--515",
journal = "ETRI Journal",
issn = "1225-6463",
publisher = "ETRI",
number = "4",

}

TY - JOUR

T1 - Shock graph for representation and modeling of posture

AU - Tahir, Nooritawati Md

AU - Hussain, Aini

AU - Abdul Samad, Salina

AU - Husain, Hafizah

PY - 2007/8

Y1 - 2007/8

N2 - Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.

AB - Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.

KW - Decision tree

KW - Human posture

KW - Medial axis

KW - Shock graph

KW - Skeletonization

UR - http://www.scopus.com/inward/record.url?scp=34548047231&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548047231&partnerID=8YFLogxK

M3 - Article

VL - 29

SP - 507

EP - 515

JO - ETRI Journal

JF - ETRI Journal

SN - 1225-6463

IS - 4

ER -