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

Jun WANG; Yulian LI; Zaiyu PAN

doi:10.1587/transinf.2019EDL8119

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

Jun WANG, Yulian LI, Zaiyu PAN

Full Text Views

80

Cite this

Free PDF (1.1MB)

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E102-D No.12 pp.2628-2631

Publication Date: 2019/12/01

Publicized: 2019/09/09

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2019EDL8119

Type of Manuscript: LETTER

Category: Pattern Recognition

Authors

Jun WANG
  China University of Mining and Technology
Yulian LI
  China University of Mining and Technology
Zaiyu PAN
  China University of Mining and Technology

Keyword

hand-dorsa vein recognition, pre-trained DCNN, task-specific cross-convolutional-layer pooling

Cite this

Copy

Jun WANG, Yulian LI, Zaiyu PAN, "Hand-Dorsa Vein Recognition Based on Task-Specific Cross-Convolutional-Layer Pooling" in IEICE TRANSACTIONS on Information, vol. E102-D, no. 12, pp. 2628-2631, December 2019, doi: 10.1587/transinf.2019EDL8119.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8119/_p

Copy

@ARTICLE{e102-d_12_2628,
author={Jun WANG, Yulian LI, Zaiyu PAN, },
journal={IEICE TRANSACTIONS on Information},
title={Hand-Dorsa Vein Recognition Based on Task-Specific Cross-Convolutional-Layer Pooling},
year={2019},
volume={E102-D},
number={12},
pages={2628-2631},
abstract={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.},
keywords={},
doi={10.1587/transinf.2019EDL8119},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Hand-Dorsa Vein Recognition Based on Task-Specific Cross-Convolutional-Layer Pooling
T2 - IEICE TRANSACTIONS on Information
SP - 2628
EP - 2631
AU - Jun WANG
AU - Yulian LI
AU - Zaiyu PAN
PY - 2019
DO - 10.1587/transinf.2019EDL8119
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2019
AB - 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.
ER -