Polygonal Shape-based Features for Pose Recognition using Kernel-SVM

Research output: Contribution to journalArticle

Abstract

Pose recognition is an intriguing and challenging problem particularly in surveillance, inspection, etc. that lies in computer vision. This paper presents an efficient human walking and abnormal poses recognition system based on kernel-support vector machine (KSVM) using a novel feature set based on polygonal shape generalization on the human silhouette. The Shapiro-Wilk test was conducted to assess the data distribution and it summarized that the test rejected the hypothesis of normality for all features. Therefore, an inferential Mann-Whitney U test was performed to evaluate the proposed feature set statistically and results showed that all features were significantly different between the groups of poses (p < 0.001). Three kernel models: linear, polynomial and radial based function were adopted for SVM to classify the walking and abnormal poses. Results obtained showed that all three kernels of the KSVM classifiers performed well with accuracies of more than 95%. However, further experiments proved that the polynomial KSVM yields the best accuracy of 99.96%. Thus, it can be concluded that the proposed polygonal shape-based feature set is best paired with the polynomial KSVM for abnormal pose detection task.

Original languageEnglish
Pages (from-to)41-46
Number of pages6
JournalJournal of Telecommunication, Electronic and Computer Engineering
Volume10
Issue number2-6
Publication statusPublished - 1 Jan 2018

Fingerprint

Support vector machines
Polynomials
Computer vision
Classifiers
Inspection
Experiments

Keywords

  • Feature Extraction
  • Kernel-Support Vector Machine
  • Polygonal Shape
  • Pose Recognition.

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Polygonal Shape-based Features for Pose Recognition using Kernel-SVM. / Abu Hassan, M. F.; Hussain, Aini; Md Saad, Mohamad Hanif.

In: Journal of Telecommunication, Electronic and Computer Engineering, Vol. 10, No. 2-6, 01.01.2018, p. 41-46.

Research output: Contribution to journalArticle

@article{69f50e1e6a26457da87edc5e047251e1,
title = "Polygonal Shape-based Features for Pose Recognition using Kernel-SVM",
abstract = "Pose recognition is an intriguing and challenging problem particularly in surveillance, inspection, etc. that lies in computer vision. This paper presents an efficient human walking and abnormal poses recognition system based on kernel-support vector machine (KSVM) using a novel feature set based on polygonal shape generalization on the human silhouette. The Shapiro-Wilk test was conducted to assess the data distribution and it summarized that the test rejected the hypothesis of normality for all features. Therefore, an inferential Mann-Whitney U test was performed to evaluate the proposed feature set statistically and results showed that all features were significantly different between the groups of poses (p < 0.001). Three kernel models: linear, polynomial and radial based function were adopted for SVM to classify the walking and abnormal poses. Results obtained showed that all three kernels of the KSVM classifiers performed well with accuracies of more than 95{\%}. However, further experiments proved that the polynomial KSVM yields the best accuracy of 99.96{\%}. Thus, it can be concluded that the proposed polygonal shape-based feature set is best paired with the polynomial KSVM for abnormal pose detection task.",
keywords = "Feature Extraction, Kernel-Support Vector Machine, Polygonal Shape, Pose Recognition.",
author = "{Abu Hassan}, {M. F.} and Aini Hussain and {Md Saad}, {Mohamad Hanif}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "10",
pages = "41--46",
journal = "Journal of Telecommunication, Electronic and Computer Engineering",
issn = "2180-1843",
publisher = "Universiti Teknikal Malaysia Melaka",
number = "2-6",

}

TY - JOUR

T1 - Polygonal Shape-based Features for Pose Recognition using Kernel-SVM

AU - Abu Hassan, M. F.

AU - Hussain, Aini

AU - Md Saad, Mohamad Hanif

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Pose recognition is an intriguing and challenging problem particularly in surveillance, inspection, etc. that lies in computer vision. This paper presents an efficient human walking and abnormal poses recognition system based on kernel-support vector machine (KSVM) using a novel feature set based on polygonal shape generalization on the human silhouette. The Shapiro-Wilk test was conducted to assess the data distribution and it summarized that the test rejected the hypothesis of normality for all features. Therefore, an inferential Mann-Whitney U test was performed to evaluate the proposed feature set statistically and results showed that all features were significantly different between the groups of poses (p < 0.001). Three kernel models: linear, polynomial and radial based function were adopted for SVM to classify the walking and abnormal poses. Results obtained showed that all three kernels of the KSVM classifiers performed well with accuracies of more than 95%. However, further experiments proved that the polynomial KSVM yields the best accuracy of 99.96%. Thus, it can be concluded that the proposed polygonal shape-based feature set is best paired with the polynomial KSVM for abnormal pose detection task.

AB - Pose recognition is an intriguing and challenging problem particularly in surveillance, inspection, etc. that lies in computer vision. This paper presents an efficient human walking and abnormal poses recognition system based on kernel-support vector machine (KSVM) using a novel feature set based on polygonal shape generalization on the human silhouette. The Shapiro-Wilk test was conducted to assess the data distribution and it summarized that the test rejected the hypothesis of normality for all features. Therefore, an inferential Mann-Whitney U test was performed to evaluate the proposed feature set statistically and results showed that all features were significantly different between the groups of poses (p < 0.001). Three kernel models: linear, polynomial and radial based function were adopted for SVM to classify the walking and abnormal poses. Results obtained showed that all three kernels of the KSVM classifiers performed well with accuracies of more than 95%. However, further experiments proved that the polynomial KSVM yields the best accuracy of 99.96%. Thus, it can be concluded that the proposed polygonal shape-based feature set is best paired with the polynomial KSVM for abnormal pose detection task.

KW - Feature Extraction

KW - Kernel-Support Vector Machine

KW - Polygonal Shape

KW - Pose Recognition.

UR - http://www.scopus.com/inward/record.url?scp=85049391983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049391983&partnerID=8YFLogxK

M3 - Article

VL - 10

SP - 41

EP - 46

JO - Journal of Telecommunication, Electronic and Computer Engineering

JF - Journal of Telecommunication, Electronic and Computer Engineering

SN - 2180-1843

IS - 2-6

ER -