Palmprint Recognition Using Kernel PCA of Gabor Features


23rd International Symposium on Computer and Information Sciences (ISCIS), İstanbul, Turkey, 27 - 29 October 2008, pp.106-107 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iscis.2008.4717873
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.106-107
  • Karadeniz Technical University Affiliated: Yes


This paper presents a new method for automatic palmprint recognition based on kernel PCA method by integrating the Gabor wavelet representation of palm images. Gabor wavelets are first applied to derive desirable palmprint features. The Gabor transformed palm images exhibit strong characteristics of spatial locality, scale, and-orientation selectivity. These images can produce salient features that are most suitable for palmprint recognition. The kernel PCA method then nonlinearly maps the Gabor-wavelet image into a high-dimensional feature space. The proposed algorithm has been successfully tested on two different public data sets from the PolyU palmprint databases for which the samples were collected in two different sessions.