DFVR: Deformable finger vein recognition

Although some developments have been achieved in finger vein recognition recently, the image deformation problem has received relatively less attention and still intractable. In this paper, the reason and the harmfulness of this problem are analyzed firstly. And then, a deformable finger vein recognition framework is proposed to deal with this problem, consisting of the improved vein PCA-SIFT feature and bidirectional deformable spatial pyramid matching (BDSPM). Furthermore, we build a finger vein deformation database to imitate image deformation in real application. The experimental results, on the self-built deformation database and one public database, prove the effectiveness of the proposed framework for dealing with the image deformation problem.

1. Introduction

Finger vein recognition is a tough task if the used images have deformation problem. Image deformation in this paper mainly means all kinds of variations between vein patterns in multiple genuine images, such as, relative translations on horizontal direction. And, this kind of vein pattern deformation is generally caused by the random finger placement in contactless and unrestrained image capturing. Large vein pattern variations can decrease the similarity of genuine images, and further make false rejection in recognition.