DocumentCode :
3642734
Title :
Basic on-line handwritten signature features for personal biometric authentication
Author :
Bača Miroslav;Koruga Petra;Fotak Tomislav
Author_Institution :
Faculty for Organization and Informatics, Centre for Biometrics Pavlinska 2, 42000 Varaž
fYear :
2011
fDate :
5/1/2011 12:00:00 AM
Firstpage :
1458
Lastpage :
1463
Abstract :
On-line handwritten signature-based personal authentication is still a challenging research topic. Although great efforts have been achieved in developing and defining a framework that systems for on-line authentication based on the handwritten signature of a person should adhere, these frameworks are still not enough because they do not include all the features that handwritten signature as a biometric feature has. In addition, there is a range of features that current system for capturing a signature posses by which it is possible to further and better define the characteristics of signatures required to be in the process of authentication of entities, but can be used not only for authentication but also for identification. The paper provides an overview of the differences between off-line and on-line mode of authentication system based on the handwritten signature as well as surveys of some properties that these features can have, supported with the latest systems to "capture" handwritten signatures.
Keywords :
"Feature extraction","Authentication","Pixel","Hidden Markov models","Databases","Data mining","Artificial neural networks"
Publisher :
ieee
Conference_Titel :
MIPRO, 2011 Proceedings of the 34th International Convention
Print_ISBN :
978-1-4577-0996-8
Type :
conf
Filename :
5967290
Link To Document :
بازگشت