Hand Vein Recognition with Bag of SIFT Feature Model

DOI

10.2991/icmmita-16.2016.255How to use a DOI?

Keywords

Vein Recognition; SIFT; Mismatching; BOSF; SVM

Abstract

SIFT, which is widely used for feature extraction in image recognition task especially when image rotation, translation, uneven illumination occur, has been applied in vein recognition task more widely. However, mismatching between intra-class and inter-class, which is unbearable for personal identification task, is unavoidable under the traditional ratio-based matching framework. To solve such problem, the paper proposes bag of SIFT feature (BOSF) model to realize SIFT feature based matching framework from the perspective of feature coding and classification. Finally, the proposed approach is rigorously evaluated on the self-built database and achieves the state-of-the-art EER (Equal Error Rate) of 0.026%, which demonstrates the effectiveness of the proposed model.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fuqiang Li
AU  - Tongzhuang Zhang
AU  - Yong Liu
PY  - 2017/01
DA  - 2017/01
TI  - Hand Vein Recognition with Bag of SIFT Feature Model
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1078
EP  - 1083
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.255
DO  - 10.2991/icmmita-16.2016.255
ID  - Li2017/01
ER  -