FINGER VEIN PRESENTATION ATTACK DETECTION USING TOTAL VARIATION DECOMPOSITION

Abstract

Finger vein recognition is an emerging biometric technique for personal authentication that has garnered considerable attention in the past decade. Although shown to be effective, recent studies have revealed that finger vein biometrics is also vulnerable to presentation attacks, i.e., printed versions of authorized individual finger vein images can be used to gain access to facilities or services. In this paper, given that both blurriness and the noise distribution are slightly different between real and forged finger vein images, we propose an efficient and robust method for detecting presentation attacks that use forged finger vein images (print artifacts). First, we use total variation (TV) regularization to decompose original finger vein images into structure and noise components, which represent the degrees of blurriness and the noise distribution. Second, a block local binary pattern (LBP) descriptor is used to encode both structure and noise information in the decomposed components. Finally, we use a cascaded support vector machine (SVM) model for classification, by which finger vein presentation attacks can be effectively detected. To evaluate the performance of our approach, we constructed a new finger vein presentation attack database. Extensive experimental results gleaned from the two finger vein presentation attack databases and a palm vein presentation attack database show that our method clearly outperforms state-of-the-art methods.

Existing System

Fourier spectral energy ratio (FSER), the discrete wavelet transform (DWT), and a combination of FSER and DWT (i.e., FSER-DWT).

Proposed System

In this section, we present the methods of TV regularization, LBP, and SVMs in detail. Note that preprocessing, such as image filtering and enhancement, which would likely lead to the loss of some discriminative information, is omitted from our proposed method to guarantee its effectiveness in PAD. We used TV regularization to decompose an original image into structure and noise components, representing the degree of blurriness and the noise distribution. We then exploited block LBP descriptors and a cascaded SVM model to encode and classify candidate finger vein images. We also constructed a new finger vein presentation attack database for performance evaluation. Next, we conducted extensive experiments using three databases, including our own FVD, a public FVD, and a public PVD. The results show that our proposed method can achieve complete discrimination using both cropped and full size real and forged images, outperforming state-of-the-art methods in both intra-database and inter-database test scenarios.

Architecture

BLOCK DIAGRAM