Welcome to the InfoSci Platform
Reference Hub1
Human Face Recognition using Gabor Based Kernel Entropy Component Analysis

Human Face Recognition using Gabor Based Kernel Entropy Component Analysis

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
Copyright: © 2012 |Volume: 2 |Issue: 3 |Pages: 20
ISSN: 2155-6997|EISSN: 2155-6989|EISBN13: 9781466611276|DOI: 10.4018/ijcvip.2012070101
Cite Article Cite Article

MLA

Kar, Arindam, et al. "Human Face Recognition using Gabor Based Kernel Entropy Component Analysis." IJCVIP vol.2, no.3 2012: pp.1-20. http://doi.org/10.4018/ijcvip.2012070101

APA

Kar, A., Bhattacharjee, D., Basu, D. K., Nasipuri, M., & Kundu, M. (2012). Human Face Recognition using Gabor Based Kernel Entropy Component Analysis. International Journal of Computer Vision and Image Processing (IJCVIP), 2(3), 1-20. http://doi.org/10.4018/ijcvip.2012070101

Chicago

Kar, Arindam, et al. "Human Face Recognition using Gabor Based Kernel Entropy Component Analysis," International Journal of Computer Vision and Image Processing (IJCVIP) 2, no.3: 1-20. http://doi.org/10.4018/ijcvip.2012070101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this paper, the authors present a novel Gabor wavelet based Kernel Entropy Component Analysis (KECA) method by integrating the Gabor wavelet transformation (GWT) of facial images with the KECA method for enhanced face recognition performance. Firstly, from the Gabor wavelet transformed images the most important discriminative desirable facial features characterized by spatial frequency, spatial locality and orientation selectivity to cope with the variations due to illumination and facial expression changes were derived. After that KECA, relating to the Renyi entropy is extended to include cosine kernel function. The KECA with the cosine kernels is then applied on the extracted most important discriminating feature vectors of facial images to obtain only those real kernel ECA eigenvectors that are associated with eigenvalues having positive entropy contribution. Finally, these real KECA features are used for image classification using the L1, L2 distance measures; the Mahalanobis distance measure and the cosine similarity measure. The feasibility of the Gabor based KECA method with the cosine kernel has been successfully tested on both frontal and pose-angled face recognition, using datasets from the ORL, FRAV2D, and the FERET database.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.