e-ISSN : 0975-3397
Print ISSN : 2229-5631
Home | About Us | Contact Us

ARTICLES IN PRESS

Articles in Press

ISSUES

Current Issue
Archives

CALL FOR PAPERS

CFP 2021

TOPICS

IJCSE Topics

EDITORIAL BOARD

Editors

Indexed in

oa
 

ABSTRACT

Title : Canonical Correlated Kernel PCA Method for Face Recognition
Authors : N.NagaMounica, Ch.Ganapathy Reddy
Keywords : Face Recognition, Kernel PCA, Canonical Correlation Analyses.
Issue Date : August 2012.
Abstract :
Practical face recognition systems are sometimes confronted with low-resolution face images. To address this problem, a super-resolution method that uses nonlinear mappings to infer coherent features that favor higher recognition of the nearest neighbor (NN) classifiers for recognition of single LR face image is presented. Canonical correlation analysis is applied to establish the coherent subspaces between the principal component analyses (PCA) based features of high-resolution (HR) and LR face images. The obtained features from PCA are not good enough for dimensionality reduction and computational complexity when large set of databases are taken into consideration. To overcome that problem Kernel PCA is introduced. Then, a nonlinear mapping between HR/LR features can be built by radial basis functions (RBFs) with lower regression errors in the coherent feature space than in the KPCA feature space. Thus, we can compute super-resolved coherent features corresponding to an input LR image according to the trained RBF model efficiently and accurately. And, face identity can be obtained by feeding these super-resolved features to a simple NN classifier. Extensive experiments on the Yale database show that the proposed method outperforms the state-of-the-art face recognition algorithms for single LR image in terms of both recognition rate and robustness to facial variations of pose and expression.
Page(s) : 1454-1460
ISSN : 0975–3397
Source : Vol. 4, Issue.08

All Rights Reserved © 2009-2024 Engg Journals Publications
Page copy protected against web site content infringement by CopyscapeCreative Commons License