An Approach for Hand Vein Representation and Indexing

Abstract

This paper proposes a model for representing and indexing of hand vein images. The proposed representation model identifies the junction points and perceives the spatial relationships existing among all junction points in hand vein images by the use of triangular spatial relationship (TSR). The model preserves the TSR among the junction points in a symbolic hand vein image by the use of quadruples and for each quadruple, a unique TSR key is generated. A novel methodology to label the junction points based on graph properties of junction points is also proposed. A Symbolic Hand Vein Image Database (SHVID) is created through the construction of B-tree, an efficient multilevel indexing structure. A methodology to retrieve similar symbolic hand vein images for a given query image is also presented. The proposed methodology has shown promising results.