“…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.…”