Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value

This paper present a face detection system using Radial Basis Function Neural Networks With Fixed Spread Value. Face detection is the first step in face recognition system. The purpose is to localize and extract the face region from the background that will be fed into the face recognition system fo...

Full description

Bibliographic Details
Main Authors: A Aziz, Khairul Azha, Abdullah, Shahrum Shah, Mohd Jahari @ Mohd Johari, Ahmad Nizam
Format: Article
Language:English
Published: Serials Publications 2011
Subjects:
Online Access:http://eprints.utem.edu.my/id/eprint/4427/
http://eprints.utem.edu.my/id/eprint/4427/1/IJCSES.PDF
_version_ 1848887030524674048
author A Aziz, Khairul Azha
Abdullah, Shahrum Shah
Mohd Jahari @ Mohd Johari, Ahmad Nizam
author_facet A Aziz, Khairul Azha
Abdullah, Shahrum Shah
Mohd Jahari @ Mohd Johari, Ahmad Nizam
author_sort A Aziz, Khairul Azha
building UTeM Institutional Repository
collection Online Access
description This paper present a face detection system using Radial Basis Function Neural Networks With Fixed Spread Value. Face detection is the first step in face recognition system. The purpose is to localize and extract the face region from the background that will be fed into the face recognition system for identification. General preprocessing approach was used for normalizing the image and a Radial Basis Function (RBF) Neural Network was used to distinguish between face and non-face images. RBF Neural Networks offer several advantages compared to other neural network architecture such as they can be trained using fast two stages training algorithm and the network possesses the property of best approximation. The output of the network can be optimized by setting suitable values of the center and spread of the RBF. In this paper, a uniform fixed spread value will be used. The performance of the RBFNN face detection system will be based on the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) criteria. In this research, the best setting for RBF face detection were summarized into one table where by using center 200 and spread 4 gives the highest detection rate and the lowest FAR as well as FRR. But for detecting many faces in a single image, center 200 and spread 5 is the best setting as the system can detect all faces in the image.
first_indexed 2025-11-15T19:47:54Z
format Article
id utem-4427
institution Universiti Teknikal Malaysia Melaka
institution_category Local University
language English
last_indexed 2025-11-15T19:47:54Z
publishDate 2011
publisher Serials Publications
recordtype eprints
repository_type Digital Repository
spelling utem-44272022-01-05T14:47:05Z http://eprints.utem.edu.my/id/eprint/4427/ Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value A Aziz, Khairul Azha Abdullah, Shahrum Shah Mohd Jahari @ Mohd Johari, Ahmad Nizam TK Electrical engineering. Electronics Nuclear engineering This paper present a face detection system using Radial Basis Function Neural Networks With Fixed Spread Value. Face detection is the first step in face recognition system. The purpose is to localize and extract the face region from the background that will be fed into the face recognition system for identification. General preprocessing approach was used for normalizing the image and a Radial Basis Function (RBF) Neural Network was used to distinguish between face and non-face images. RBF Neural Networks offer several advantages compared to other neural network architecture such as they can be trained using fast two stages training algorithm and the network possesses the property of best approximation. The output of the network can be optimized by setting suitable values of the center and spread of the RBF. In this paper, a uniform fixed spread value will be used. The performance of the RBFNN face detection system will be based on the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) criteria. In this research, the best setting for RBF face detection were summarized into one table where by using center 200 and spread 4 gives the highest detection rate and the lowest FAR as well as FRR. But for detecting many faces in a single image, center 200 and spread 5 is the best setting as the system can detect all faces in the image. Serials Publications 2011-07 Article NonPeerReviewed text en http://eprints.utem.edu.my/id/eprint/4427/1/IJCSES.PDF A Aziz, Khairul Azha and Abdullah, Shahrum Shah and Mohd Jahari @ Mohd Johari, Ahmad Nizam (2011) Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value. International Journal of Computer Sciences and Engineering Systems, 5 (3). pp. 145-151. ISSN 0973-4406 http://bit.kuas.edu.tw/~ijcses/
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
A Aziz, Khairul Azha
Abdullah, Shahrum Shah
Mohd Jahari @ Mohd Johari, Ahmad Nizam
Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title_full Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title_fullStr Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title_full_unstemmed Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title_short Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value
title_sort face detection using radial basis function neural networks with fixed spread value
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.utem.edu.my/id/eprint/4427/
http://eprints.utem.edu.my/id/eprint/4427/
http://eprints.utem.edu.my/id/eprint/4427/1/IJCSES.PDF