Palmprint-Palmvein Fusion Recognition Based on Deep Hashing Network

Abstract

Palmprint attracts increasing attention due to its several advantages in the biometrics field. Deep learning has achieved remarkable performance in the computer vision area, so a large number of deep-learning-based methods have been proposed by the research community for palmprint recognition. The outputs of a deep hashing network (DHN) can be represented as binary bit string, so DHN can reduce the storage and accelerate matching/retrieval speed. In this paper, DHN is employed to extract the binary template for palmprint and palmvein verification. Spatial transformer network is used to overcome the rotation and dislocation. Palmprint and palmvein can be acquired from visible-light spectrums, including red (R), green (G), blue (B), and near infrared (NIR) spectrum, respectively. Since the features in different spectrums are different, their complementary advantages can be exploited to the full by fusion. Image-level fusion and score-level fusion are developed for palmprint-palmvein fusion recognition. The sufficient experiments demonstrate that score-level fusion can improve the accuracy efficiently.

Presentation Attacks in Palmprint Recognition Systems

“…CompNet has lower equal error rate compared with the existing methods, and has fewer parameters in the network, so it is easy to train. Wu et al [41] realized multi-spectral palmprint fusion, and reduce the variance between intra-class score and inter-class score [42]. Moreover, this method saves storage space and matching computation.…”

Extraction of intersecting palm‐vein and palmprint features for cancellable identity verification

“…The handcrafted methods include Adaptive Gabor filter (Adapt-Gabor) [76], Local Directional Pattern (LDP) [16], Veincode [6], Local Tetra Patterns (LTrP) [44], SIFT [10], ORB [11], Mutual Foreground-Based Local Binary Pattern (MFLBP) [77], LDBC [41], and BTP [78]. The deep learning-based models include PVSNet [79], DenseNet-161 [80], Inception-v3 [81], Vein-CNN [82], VGG-19 [83], Vein-transfer [84], FaceNet [85], DBN [13], DenseNet-initialisation [86], DHN [34], PalmNet [87], and PalmCohashNet [36]. In the comparison, the results of LDBC, BTP, DenseNet-161, Inception-v3, VGG-19, PVSNet, Vein-CNN, FaceNet, Vein-transfer, DBN, DenseNetinitialisation, DHN, PalmNet, and PalmCohashNet were taken from refs.…”

“…In the comparison, the results of LDBC, BTP, DenseNet-161, Inception-v3, VGG-19, PVSNet, Vein-CNN, FaceNet, Vein-transfer, DBN, DenseNetinitialisation, DHN, PalmNet, and PalmCohashNet were taken from refs. [13,34,36,41,78,79,84,86,87] since they adopted the same experimental protocol as ours utilising the PolyU-M, CASIA, and IITD databases.…”

“…They also employed a simplified LBP to strengthen the discriminative power of the extracted templates. Recently, Wu et al [34] utilised a deep hashing network for palmprint and palm-vein verification, harnessing the efficiency of binary bit string templates. They adopted both feature-level and score-level fusion to enhance their performance.…”

Phase-Based Palmprint Identification With Convolutional Sparse Coding

“…Shao et al [30] considered the combination of Deep Distillation Hashing (DDH) and knowledge distillation to build a compact CNN model for palmprint recognition. Wu et al [31] considered extracting the binary template from palmprint and palmvein images using deep hashing network. Xu et al [32] proposed an accurate method for palmprint recognition by transfer learning of CNN pre-trained with soft biometrics for palmprints.…”