Extraction and Cross-Matching of Palm-Vein and Palmprint From the RGB and the NIR Spectrums for Identity Verification

Biometric recognition systems based on 3D palmprint captured with optical technology have been widely investigated in the last decade; however, they can provide information about the external skin surface only. This limit can be overcome by Ultrasound, which allows gaining information on the depth of palm lines and can verify the liveness of the sample, making the recognition systems very hard to fake. In this work, a feasible palmprint recognition system based on 3D ultrasound images is proposed. Unlike previous wet setups, the coupling between probe and human is realized through a gel pad, which permits a comfortable and precise positioning of the hand by the user. Collected 3D images are processed to generate 2D palmprint images at various under-skin depths. 2D features are then extracted from these images, experimenting with different procedures, and are merged to define a 3D template that contains lines' depth information. Recognition performances were evaluated by performing verification and identification experiments on a home-made database composed of 423 samples from 55 volunteers. An EER rate of 0.36% and an identification accuracy of 100% are obtained. The suitability of the proposed system in secure access control applications is finally discussed.

Section: Introductionmentioning

confidence: 99%

A Feasible 3D Ultrasound Palmprint Recognition System for Secure Access Control Applications

Iula

Micucci

2021

“…where 0 0 0 and I I I denote respectively the zero and the identity matrices. A projection operation on an image X X X by k pixels of shift to the horizontal direction is obtained by [11]- [14], [16]- [20], [22], [52], [53] (c) Nil Palmprint (d) [23], [24], [27]- [30] (e) [54] (f) [25], [26], [31]- [36] Palm-vein + palmprint (g) [55] (h) [15], [48], [56]- [58] (i) [50] a : The conference presentation [21] was a preliminary work of the current proposal. b : The current manuscript has lower than 10% of content overlap with that of [21].…”

Section: B Shift Matrixmentioning

confidence: 99%

“…This is due to the high penetrability of long wavelength of the IR and the NIR rays into the skin tissues to reach the blood vessels [17]. The RGB palm-vein is only partially visible due to the relatively low penetration of the visible imaging spectrum [21], [49], [50]. Although certain information can be lost, the partial information constitutes an additional attribute for biometric authentication.…”

Section: Introductionmentioning

confidence: 99%

Palm-Vein Verification Using Images From the Visible Spectrum

Cho

Kim

et al. 2021

Self Cite

In this paper, we investigate into utilization of images from the visible light (RGB) spectrum for identity verification based on the palm-veins. This is differentiated from the commonly utilized Nearinfrared (NIR) images for palm-vein feature extraction. Our goal is to explore into the often omitted palm-vein information from the RGB palm images considering the vast deployment of the RGB cameras. Essentially, the vein line features are extracted at various scales based on an efficient difference image projection. The extracted features from the gallery and the probe images are matched based on a modified Hamming distance measure. The resultant similarity scores are finally fused at score level for accuracy enhancement. Experiments are conducted on two public multi-spectral palm databases. The results show encouraging matching accuracy and computational efficiency of the proposed method which extracts the palm-vein utilizing only the visible spectrum. The outcome of this study can be deployed as a standalone biometric or as part of a multibiometric system for secured authentication.

“…is a finite-dimensional coefficient matrix, and By substituting in the defined transformation function and adding the regularization term to Eq. 7, the following regularized least squares function can be obtained: 10) where the first term can be seen as a weighted empirical function; the second term, which is called the Tikhonov regularization term, encourages all L points to move together as a group and helps to preserve the topological structure of X by ensuring that the global connectivity and associativity are retained; and the positive real number 1…”

Section: Global Topological Constraintmentioning

confidence: 99%

“…It is more challenging because the correspondences between the two point sets are more difficult to establish and the underlying nonrigid spatial transformations are complicated. However, nonrigid registration arises in many practical engineering and science tasks, including nonrigid palmprint image registration [10], facial expression recognition [11], visual navigation [12], etc.…”

Section: Introductionmentioning

confidence: 99%

A Unified Framework for Nonrigid Point Set Registration via Coregularized Least Squares

Yang

Liu

et al. 2020

This paper describes a method for performing nonrigid point set registration on data with different kinds of degradation (deformation, occlusion, noise, and outliers). We formulate the registration problem as a mixture model estimation problem by employing two topologically complementary constraints in a Gaussian mixture model (GMM)-based learning framework. The first constraint is Tikhonov-based regularization, which maintains the overall spatial connectivity by moving the point set collectively and coherently. The second constraint is graph-Laplacian-based regularization embedding, which preserves the intrinsic topological characteristics of the marginal space during registration. Hence, the proposed method is named coregularized least squares (Co-RLS). Our method iteratively estimates the correspondences and nonrigid transformation between two given sets of points. First, the correspondences are established subject to the ordering information of the contour points using feature descriptors, i.e., the shape context. Then, the transformation is recovered by minimizing the Co-RLS function, and the expectation maximization method is used to update the transformation parameters and outlier ratios. Experimental results on various types of synthetic and real data show the superior effectiveness and robustness of the proposed method compared with other state-of-the-art methods.