Comparison of PCA -, MDF -, and RD-LDA - based feature extraction approaches for hand-based personal recognition

Authors:
Nikola Pavešić;Slobodan Ribarić;Benjamin Grad
Affiliations:
University of Ljubljana;University of Zagreb;University of Ljubljana
Venue:
CompSysTech '07 Proceedings of the 2007 international conference on Computer systems and technologies
Year:
2007

Citing 5
Cited 1

Using Discriminant Eigenfeatures for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition
Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition

Pattern Recognition Letters
A Biometric Identification System Based on Eigenpalm and Eigenfinger Features

IEEE Transactions on Pattern Analysis and Machine Intelligence

Single-sensor multi-instance fingerprint and eigenfinger recognition using (weighted) score combination methods

International Journal of Biometrics

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, Principal Component Analysis (PCA), Most Discriminant Features (MDF), and Regularized-Direct Linear Discriminant Analysis (RD-LDA) - based feature extraction approaches are tested and compared in an experimental personal recognition system. The system is multimodal and bases on features extracted from nine regions of an image of the palmar surface of the hand. For testing purposes 10 gray-scale images of right hand of 184 people were acquired. The experiments have shown that the best results are obtained with the RD-LDA - based features extraction approach (100% correctness for 920 identification tests and EER = 0.01% for 64170 verification tests).