Astroid shaped DCT feature extraction for enhanced face recognition

Authors:
R. Divya;Anwesha Rath;S. Ramachandran;K. Manikantan
Affiliations:
M.S. Ramaiah Institute of Technology, Bangalore, India;M.S. Ramaiah Institute of Technology, Bangalore, India;S.J.B. Institute of Technology, Bangalore, India;M.S. Ramaiah Institute of Technology, Bangalore, India
Venue:
Proceedings of the CUBE International Information Technology Conference
Year:
2012

Citing 10
Cited 0

Face Recognition Using the Discrete Cosine Transform

International Journal of Computer Vision - Special issue: Research at McGill University
Kernel Eigenfaces vs. Kernel Fisherfaces: Face Recognition Using Kernel Methods

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
An improved face recognition technique based on modular PCA approach

Pattern Recognition Letters
Enhanced (PC)2 A for face recognition with one training image per person

Pattern Recognition Letters
Analysis of the publications on the applications of particle swarm optimisation

Journal of Artificial Evolution and Applications - Regular issue
Semi-random subspace method for face recognition

Image and Vision Computing
Feature Extraction & Image Processing, Second Edition

Feature Extraction & Image Processing, Second Edition
Comparing and combining lighting insensitive approaches for face recognition

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel Discrete Cosine Transform (DCT) spectrum based approach to enhance the performance of a face recognition (FR) system employing a unique astroid shaped feature selection from the DCT spectrum. Individual stages of the FR system are examined and an attempt is made to improve each stage. A Binary Particle Swarm Optimization (BPSO)-based feature selection algorithm is used to search the feature vector space for the optimal feature subset. Experimental results show the promising performance of astroid shaped DCT feature extraction for face recognition on ORL, UMIST, Extended Yale B and Color FERET databases.