Does EigenPalm work? A System and Evaluation Perspective

Authors:
King-Hong Cheung;Adams Kong;David Zhang;Mohamed Kamel;Jane You
Affiliations:
Hong Kong Polytechnic University, Hung Hom, Hong Kong;Hong Kong Polytechnic University, Hung Hom, Hong Kong;Hong Kong Polytechnic University, Hung Hom, Hong Kong;University of Waterloo, Canada;Hong Kong Polytechnic University, Hung Hom, Hong Kong
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Year:
2006

Citing 0
Cited 5

Three measures for secure palmprint identification

Pattern Recognition
Palmprint recognition with improved two-dimensional locality preserving projections

Image and Vision Computing
Personal Recognition Using Single-Sensor Multimodal Hand Biometrics

ICISP '08 Proceedings of the 3rd international conference on Image and Signal Processing
A Comparative Study of Palmprint Recognition Algorithms

ACM Computing Surveys (CSUR)
A novel classification method for palmprint recognition based on reconstruction error and normalized distance

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, there are keen interests in EigenPalm, which, collectively, refers to those methods that extract palmprint features directly from the appearance by means of Principal Component Analysis (PCA) for (dis)similarity matching. Encouraging results have been reported with the use of EigenPalm. However, we find a different story under a system and evaluation perspective. In this paper, we would like to introduce three issues that should be considered: the effects of templates from two different sessions, the effects of identical twins and the effects of unseen subjects. They are missing in the previous studies of EigenPalm.