Title :
Use of polynomial classifiers for on-line signature recognition
Author :
Maiorana, Emanuele ; Campisi, Patrizio ; La Rocca, D. ; Scarano, Gaetano
Author_Institution :
Dept. of Appl. Electron., Univ. Roma Tre, Rome, Italy
Abstract :
In this paper we propose a system exploiting polynomial classifiers, typically employed in identification scenarios, for the case of user verification based on on-line signature. In order to accomplish this task, a novel strategy for generating synthetic classes of signature features is proposed. The proposed system guarantees high verification performance while requiring low complexity and low storage capacity for the employed users´ templates. Experimental tests conducted over the public MCYT database show the effectiveness of the proposed approach.
Keywords :
handwriting recognition; pattern classification; polynomials; storage management; complexity capcity; employed users templates; identification scenarios; online signature recognition; polynomial classifiers; public MCYT database; signature features; storage capacity; user verification; verification performance; Biometrics (access control); Databases; Feature extraction; Forgery; Polynomials; Training; Vectors;
Conference_Titel :
Biometrics: Theory, Applications and Systems (BTAS), 2012 IEEE Fifth International Conference on
Conference_Location :
Arlington, VA
Print_ISBN :
978-1-4673-1384-1
Electronic_ISBN :
978-1-4673-1383-4
DOI :
10.1109/BTAS.2012.6374587