ONLINE SIGNATURE RECOGNITION USING NEURAL NETWORK

Here it discusses about some of the features of signature data and their extraction from the raw data set collected from ATVS signature database. The features include time duration, sign changes of dx/dt and dy/dt, average jerk, number of pen-up pen-down etc. Signature features are pre-processed and brought to a value having same decimal point and trained using back propagation neural network. For signature data of 10 users and accuracy rate of 86% is obtained.

[1]  H. N. Prakash,et al.  Online Signature Verification and Recognition: An Approach Based on Symbolic Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Suh-Yin Lee,et al.  On-line signature verification based on logarithmic spectrum , 1998, Pattern Recognit..

[3]  E. Kishon,et al.  Use of dynamic features for signature verification , 1991, Conference Proceedings 1991 IEEE International Conference on Systems, Man, and Cybernetics.

[4]  Santanu Chaudhury,et al.  Signature verification using multiple neural classifiers , 1997, Pattern Recognit..

[5]  Anil K. Jain,et al.  Fusion of Local and Regional Approaches for On-Line Signature Verification , 2005, IWBRS.

[6]  Anil K. Jain,et al.  On-line signature verification, , 2002, Pattern Recognit..

[7]  V. S. Nalwa.  Automatic on-line signature verification , 1997 .

[8]  Marcos Faúndez-Zanuy,et al.  On-line signature recognition based on VQ-DTW , 2007, Pattern Recognit..