Pengecaman insan berasaskan kaedah profil sentroid dan pengelas rangkaian neural buatan

Translated title of the contribution: Human identification method based on centroid profile and artificial neural network classifier

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this study, centroidal profile which is a model based approach is employed for human recognition task. This is done by extracting unique representation of gait features of the subject automatically and passively from static images of human or non human. To evaluate the effectiveness of the generated centroidal profile, Artificial Neural Network (RNB) is used as classifier. Results attained proven that the centroidal profile is appropriate as feature extraction to be used as feature vectors for human shape classification based on classification rate of RNB achieved specifically above 98%.

Original languageUndefined/Unknown
Pages (from-to)69-79
Number of pages11
JournalJurnal Teknologi
Volume53
Publication statusPublished - Sep 2010

Fingerprint

Classifiers
Neural networks
Feature extraction

Keywords

  • Artificial neural network (ANN)
  • Centroidal profile
  • Human recognition

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Pengecaman insan berasaskan kaedah profil sentroid dan pengelas rangkaian neural buatan. / Tahir, Nooritawati Md; Hussain, Aini; Abdul Samad, Salina; Husain, Hafizah.

In: Jurnal Teknologi, Vol. 53, 09.2010, p. 69-79.

Research output: Contribution to journalArticle

@article{cd5f5cf2ae454318b45006287b415259,
title = "Pengecaman insan berasaskan kaedah profil sentroid dan pengelas rangkaian neural buatan",
abstract = "In this study, centroidal profile which is a model based approach is employed for human recognition task. This is done by extracting unique representation of gait features of the subject automatically and passively from static images of human or non human. To evaluate the effectiveness of the generated centroidal profile, Artificial Neural Network (RNB) is used as classifier. Results attained proven that the centroidal profile is appropriate as feature extraction to be used as feature vectors for human shape classification based on classification rate of RNB achieved specifically above 98{\%}.",
keywords = "Artificial neural network (ANN), Centroidal profile, Human recognition",
author = "Tahir, {Nooritawati Md} and Aini Hussain and {Abdul Samad}, Salina and Hafizah Husain",
year = "2010",
month = "9",
language = "Undefined/Unknown",
volume = "53",
pages = "69--79",
journal = "Jurnal Teknologi",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",

}

TY - JOUR

T1 - Pengecaman insan berasaskan kaedah profil sentroid dan pengelas rangkaian neural buatan

AU - Tahir, Nooritawati Md

AU - Hussain, Aini

AU - Abdul Samad, Salina

AU - Husain, Hafizah

PY - 2010/9

Y1 - 2010/9

N2 - In this study, centroidal profile which is a model based approach is employed for human recognition task. This is done by extracting unique representation of gait features of the subject automatically and passively from static images of human or non human. To evaluate the effectiveness of the generated centroidal profile, Artificial Neural Network (RNB) is used as classifier. Results attained proven that the centroidal profile is appropriate as feature extraction to be used as feature vectors for human shape classification based on classification rate of RNB achieved specifically above 98%.

AB - In this study, centroidal profile which is a model based approach is employed for human recognition task. This is done by extracting unique representation of gait features of the subject automatically and passively from static images of human or non human. To evaluate the effectiveness of the generated centroidal profile, Artificial Neural Network (RNB) is used as classifier. Results attained proven that the centroidal profile is appropriate as feature extraction to be used as feature vectors for human shape classification based on classification rate of RNB achieved specifically above 98%.

KW - Artificial neural network (ANN)

KW - Centroidal profile

KW - Human recognition

UR - http://www.scopus.com/inward/record.url?scp=84857426308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857426308&partnerID=8YFLogxK

M3 - Article

VL - 53

SP - 69

EP - 79

JO - Jurnal Teknologi

JF - Jurnal Teknologi

SN - 0127-9696

ER -