Hand-Dorsa Vein Recognition Based on Task-Specific Cross-Convolutional-Layer Pooling

Jun WANG  Yulian LI  Zaiyu PAN  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.12   pp.2628-2631
Publication Date: 2019/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDL8119
Type of Manuscript: LETTER
Category: Pattern Recognition
hand-dorsa vein recognition,  pre-trained DCNN,  task-specific cross-convolutional-layer pooling,  

Full Text: FreePDF(1.1MB)

Hand-dorsa vein recognition is solved based on the convolutional activations of the pre-trained deep convolutional neural network (DCNN). In specific, a novel task-specific cross-convolutional-layer pooling is proposed to obtain the more representative and discriminative feature representation. Rigorous experiments on the self-established database achieves the state-of-the-art recognition result, which demonstrates the effectiveness of the proposed model.