8. 3D Palmprint Classification by Global Features

Three-dimensional palmprint has proved to be a significant biometrics for personal authentication. Three-dimensional palmprints are harder to counterfeit than two-dimensional palmprints and more robust to variations in illumination and serious scrabbling on the palm surface. Previous work on three-dimensional palmprint recognition has concentrated on local features such as texture and lines. In this chapter, we propose three novel global features of three-dimensional palmprints which describe shape information and can be used for coarse matching and indexing to improve the efficiency of palmprint recognition, especially in very large databases. The three proposed shape features are Maximum Depth of palm center, Horizontal Cross-section Area of different levels and Radial Line Length from the centroid to the boundary of three-dimensional palmprint horizontal cross-section of different levels. We treat these features as a column vector and use Orthogonal Linear Discriminant Analysis to reduce their dimensionality. We then adopt two schemes: (1) coarse-level matching and (2) Ranking Support Vector Machine to improve the efficiency of palmprint recognition. We conducted a series of three-dimensional palmprint recognition experiments using an established three-dimensional palmprint database and the results demonstrate that the proposed method can greatly reduce penetration rates.