302
Copyright © 2016, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 17
DOI: 10.4018/978-1-4666-8737-0.ch017
ABSTRACT
Biometrics refers to metrics related to human characteristics and Traits. Face Recognition is the process
of identifcation of a person by their facial image. It has been an active area of research for several de-
cades, but still remains a challenging problem because of the complexity of the human face. The objective
is to authenticate a person, to have a FAR and FRR very low. This project introduces a new approach
for face recognition system using FFT algorithm. The database that contains the images is named as
train database and the test image which is stored in test database is compared with the created train
database. For further processing RGB data is converted into grayscale, thus reduces the matrix dimen-
sion. FFT is applied to the entire database and mean value of the images is computed and the same is
repeated on test database also. Based on the threshold value of the test image, face recognition is done.
Performance evaluation of Biometrics is done for normal image, skin color image, ageing image and
blur image using False Acceptance Rate(FAR), False Rejection Rate(FRR), Equal Error Rate(EER) and
also calculated the accuracy of diferent images.
1. INTRODUCTION
1.1 Biometrics
Biometrics is an emerging field of information technology which aims to identification of an individual.
Biometric identifiers are the distinctive, measurable characteristics used to label and describe individu-
als (Jain, Hong, & Pankanti, 2000). Biometric identifiers are often categorized as physiological versus
behavioral characteristics (Jain, & Ross, 2008).. It has been shown that information characteristics of each
individual can be extracted in order to verify the identity of that individual in a population. Biometric
Face Recognition using
Fast Fourier Transform
Shivakumar Baragi
BVBCET, India
Nalini C. Iyer
BVBCET, India