A handwritten signature recognition system based on LSVM

DOI

10.2991/iccse-15.2015.89How to use a DOI?

Keywords

VSM, LSVM, Handwritten signature recognition, Recognition rate

Abstract

Handwritten signature recognition has a wide application prospect in the field of identity identification. This paper presents a shape feature, dynamic feature extraction and recognition technology of LSVM state based on the combination of handwritten signature recognition system. Objective function changes in the experimental model of SVM, to LSVM, to avoid decomposition when solving the multiple solution algorithm of the problems existing in the SVM, for the purpose of improving the operating time of the system. The experimental results show that it has a high recognition rate and faster recognition rate.

Copyright

© 2015, 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  - Jie ping Chen
PY  - 2015/07
DA  - 2015/07
TI  - A handwritten signature recognition system based on LSVM
BT  - Proceedings of the 2015 International Conference on Computational Science and Engineering
PB  - Atlantis Press
SP  - 481
EP  - 487
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccse-15.2015.89
DO  - 10.2991/iccse-15.2015.89
ID  - Chen2015/07
ER  -