Palmprint identification based on wide principal lines

Abstract

In this paper, a novel palmprint identification and verification algorithm is proposed based on wide principal lines. A set of wide principal line extractors are devised. Later these wide principal line extractors are used to extract the wide principal lines. Morphological operators and grouping functions are used to eliminate the noise. In matching stage, a matching algorithm, based on pixel-to-pixel comparison is devised to calculate the similarity between the palmprints. In identification stage, wavelets and principal component analysis (PCA) are used for dimensionality reduction. Then Locally Discriminating Projection (LDP) is used to get the indexed list and the user is identified based on matching algorithm. The experimental results for the verification and identification on PolyU Database and Sub2D database are provided by Hong Kong Polytechnic University show that the discrimination of wide principal lines is also strong. With a minimum number of verifications, user is identified on these databases. © 2012 ACM.