Fourier descriptor for pedestrian shape recognition using support vector machine

Nooritawati Md Tahir, Aini Hussain, Mohd. Marzuki Mustafa, Salina Abdul Samad, Hafizah Husin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

The main objective of this study is to analyse Fourier Descriptor (FD) as feature vectors for pedestrian shape representation and recognition. FD is chosen since it is the best known boundary based shape descriptor and has proven to outperform most other boundary based methods in terms of accuracy. FD is also invariant to geometric transformations and has good noise tolerance. Initial results showed that using 10 descriptors of both low and high frequency components of pedestrian and vehicle shapes are sufficient for recognition based on high classification rate achieved. Moreover, the tremendous performance of Support Vector Machine (SVM) as classifier is confirmed based on the Kappa Score calculated. These findings have proven that our method is an effective approach for pedestrian recognition.

Original languageEnglish
Title of host publicationISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology
Pages636-641
Number of pages6
DOIs
Publication statusPublished - 2007
EventISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology - Cairo
Duration: 15 Dec 200718 Dec 2007

Other

OtherISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology
CityCairo
Period15/12/0718/12/07

Fingerprint

Support vector machines
Classifiers

Keywords

  • Fourier descriptor (FD)
  • Kappa score
  • Pedestrian
  • Support vector machine (SVM)

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Signal Processing

Cite this

Tahir, N. M., Hussain, A., Mustafa, M. M., Abdul Samad, S., & Husin, H. (2007). Fourier descriptor for pedestrian shape recognition using support vector machine. In ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology (pp. 636-641). [4458054] https://doi.org/10.1109/ISSPIT.2007.4458054

Fourier descriptor for pedestrian shape recognition using support vector machine. / Tahir, Nooritawati Md; Hussain, Aini; Mustafa, Mohd. Marzuki; Abdul Samad, Salina; Husin, Hafizah.

ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology. 2007. p. 636-641 4458054.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tahir, NM, Hussain, A, Mustafa, MM, Abdul Samad, S & Husin, H 2007, Fourier descriptor for pedestrian shape recognition using support vector machine. in ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology., 4458054, pp. 636-641, ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology, Cairo, 15/12/07. https://doi.org/10.1109/ISSPIT.2007.4458054
Tahir NM, Hussain A, Mustafa MM, Abdul Samad S, Husin H. Fourier descriptor for pedestrian shape recognition using support vector machine. In ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology. 2007. p. 636-641. 4458054 https://doi.org/10.1109/ISSPIT.2007.4458054
Tahir, Nooritawati Md ; Hussain, Aini ; Mustafa, Mohd. Marzuki ; Abdul Samad, Salina ; Husin, Hafizah. / Fourier descriptor for pedestrian shape recognition using support vector machine. ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology. 2007. pp. 636-641
@inproceedings{5b42e5e2ab6d4140a2546ae045353bad,
title = "Fourier descriptor for pedestrian shape recognition using support vector machine",
abstract = "The main objective of this study is to analyse Fourier Descriptor (FD) as feature vectors for pedestrian shape representation and recognition. FD is chosen since it is the best known boundary based shape descriptor and has proven to outperform most other boundary based methods in terms of accuracy. FD is also invariant to geometric transformations and has good noise tolerance. Initial results showed that using 10 descriptors of both low and high frequency components of pedestrian and vehicle shapes are sufficient for recognition based on high classification rate achieved. Moreover, the tremendous performance of Support Vector Machine (SVM) as classifier is confirmed based on the Kappa Score calculated. These findings have proven that our method is an effective approach for pedestrian recognition.",
keywords = "Fourier descriptor (FD), Kappa score, Pedestrian, Support vector machine (SVM)",
author = "Tahir, {Nooritawati Md} and Aini Hussain and Mustafa, {Mohd. Marzuki} and {Abdul Samad}, Salina and Hafizah Husin",
year = "2007",
doi = "10.1109/ISSPIT.2007.4458054",
language = "English",
isbn = "9781424418350",
pages = "636--641",
booktitle = "ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology",

}

TY - GEN

T1 - Fourier descriptor for pedestrian shape recognition using support vector machine

AU - Tahir, Nooritawati Md

AU - Hussain, Aini

AU - Mustafa, Mohd. Marzuki

AU - Abdul Samad, Salina

AU - Husin, Hafizah

PY - 2007

Y1 - 2007

N2 - The main objective of this study is to analyse Fourier Descriptor (FD) as feature vectors for pedestrian shape representation and recognition. FD is chosen since it is the best known boundary based shape descriptor and has proven to outperform most other boundary based methods in terms of accuracy. FD is also invariant to geometric transformations and has good noise tolerance. Initial results showed that using 10 descriptors of both low and high frequency components of pedestrian and vehicle shapes are sufficient for recognition based on high classification rate achieved. Moreover, the tremendous performance of Support Vector Machine (SVM) as classifier is confirmed based on the Kappa Score calculated. These findings have proven that our method is an effective approach for pedestrian recognition.

AB - The main objective of this study is to analyse Fourier Descriptor (FD) as feature vectors for pedestrian shape representation and recognition. FD is chosen since it is the best known boundary based shape descriptor and has proven to outperform most other boundary based methods in terms of accuracy. FD is also invariant to geometric transformations and has good noise tolerance. Initial results showed that using 10 descriptors of both low and high frequency components of pedestrian and vehicle shapes are sufficient for recognition based on high classification rate achieved. Moreover, the tremendous performance of Support Vector Machine (SVM) as classifier is confirmed based on the Kappa Score calculated. These findings have proven that our method is an effective approach for pedestrian recognition.

KW - Fourier descriptor (FD)

KW - Kappa score

KW - Pedestrian

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=58349115200&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349115200&partnerID=8YFLogxK

U2 - 10.1109/ISSPIT.2007.4458054

DO - 10.1109/ISSPIT.2007.4458054

M3 - Conference contribution

AN - SCOPUS:58349115200

SN - 9781424418350

SP - 636

EP - 641

BT - ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology

ER -