An on-line signature verification system exploiting both global and local information through decision-level fusion is presented. Global information is extracted with a feature-based representation and recognized by using Parzen Windows Classifiers. Local information is extracted as time functions of various dynamic properties and recognized by using Hidden Markov Models. Experimental results are given on the large MCYT signature database (330 signers, 16500 signatures) for random and skilled forgeries. Preliminary feature selection experiments based on feature ranking are carried out. It is shown experimentally that the machine expert based on local information outperforms the system based on global analysis when enough training data is available. Conversely, it is found that global analysis is more appropriate in the case of small training set size. The two proposed systems are also shown to give complementary recognition information which is successfully exploited using decision-level score fusion
Fierrez Aguilar, J., Nanni, L., Lopez Penalba, J., Ortega Garcia, J., Maltoni, D. (2005). An On-Line Signature Verification System Based on Fusion of Local and Global Information. NEW YORK : Springer.
An On-Line Signature Verification System Based on Fusion of Local and Global Information
NANNI, LORIS;MALTONI, DAVIDE
2005
Abstract
An on-line signature verification system exploiting both global and local information through decision-level fusion is presented. Global information is extracted with a feature-based representation and recognized by using Parzen Windows Classifiers. Local information is extracted as time functions of various dynamic properties and recognized by using Hidden Markov Models. Experimental results are given on the large MCYT signature database (330 signers, 16500 signatures) for random and skilled forgeries. Preliminary feature selection experiments based on feature ranking are carried out. It is shown experimentally that the machine expert based on local information outperforms the system based on global analysis when enough training data is available. Conversely, it is found that global analysis is more appropriate in the case of small training set size. The two proposed systems are also shown to give complementary recognition information which is successfully exploited using decision-level score fusionI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
