|
Back Issues of Engineering & Technology in India - From February 2016
HOME PAGE
BOOKS FOR YOU TO READ AND DOWNLOAD FREE!
BACK ISSUES
- E-mail your articles and book-length reports to engineeringandtechnologyindia@gmail.com.
- Your articles and book-length reports should be written following standard Stylesheets such as ASME reference and citation models.
- The Editorial Board has the right to accept, reject, or suggest modifications to the articles submitted for publication, and to make suitable stylistic adjustments. High quality, academic integrity, ethics and morals are expected from the authors and discussants.
Would you like to announce the dates and venues of your conferences, seminars, etc., and also publish the outline proceedings of these programs? Send a report to Engineering & Technology in India, engineeringandtechnologyindia@gmail.com..
Copyright © 2015
M. S. Thirumalai
Publisher: M.S. Thirumalai
11249 Oregon Circle
Bloomington, MN 55438
USA
|
Efficient Face Recognition Method for
Person Authentication
Karthick K., M.E.
Sughapriya N., M.E. Student
Abstract
In this paper, we propose efficient methods for face recognition which provides better performance for given images which might be taken in presence of different lighting conditions and slight pose variations. Face detection is performed through segmentation and face region coordinate computation. In face recognition process for each training sample the distance metric is learned to find the similarities between images. In order to raise the efficiency of face recognition, a method based on distance metric learning and hybrid neural network (back-propagation (BP) neural network and probabilistic neural network (PNN) integration) was introduced. This method based on FFT in feature extraction, distance metric data is propagated into the HNN and outputs the classification and recognition results by relative voting method. The performance analysis comparison proves the superiority of the proposed method.
Keywords: Face detection, face recognition, distance learnng,hybrid neural network.
I. INTRODUCTION
Face recognition can be categorized into two classes: face verification and face identification. The first aims to verify whether a given pair of face images/video is from the same person or not, and the second aims to recognize the given face image from a gallery set and find the most matched one. In this work, we focus on face detection and identification, which aims to determine whether a given pair of face images captured in unconstrained environments is from the same person or not. Images containing faces are essential to intelligent vision-based human computer interaction, person identification and verification.
This is only the beginning part of the article. PLEASE CLICK HERE TO READ THE ENTIRE ARTICLE IN PRINTER-FRIENDLY VERSION.
Karthick K., M.E.
Assistant Professor
karthickks.karthick@gmail.com
Sughapriya N, M.E. Student
Sugha07@gmail.com
Department of Electronics & Communication Engineering
Sri Subramanya College of Engineering & Technology
NH - 209, Sukkamanaickenpatti
Palani 624615
Tamil Nadu
India
CONTACT EDITOR
|