Title :
Signature Verification Using N-tuple Learning Machine
Author :
Maneechot, Thanin ; Kitjaidure, Yuttana
Author_Institution :
Electron. Dept., King Mongkut´´s Inst. of Technol., Bangkok
Abstract :
This research presents new algorithm for signature verification using N-tuple learning machine. The features are taken from handwritten signature on digital tablet (on-line). This research develops recognition algorithm using four features extraction, namely horizontal and vertical pen tip position (x-y position), pen tip pressure, and pen altitude angles. Verification use s N-tuple technique with Gaussian thresholding
Keywords :
Gaussian processes; feature extraction; handwriting recognition; learning (artificial intelligence); Gaussian thresholding; N-tuple learning machine; digital tablet; features extraction; handwritten signature; horizontal pen tip position; on-line signature verification; pen altitude angles; pen tip pressure; recognition algorithm; vertical pen tip position; Credit cards; Data acquisition; Data security; Feature extraction; Handwriting recognition; Helium; Image converters; Machine learning; Sampling methods; Transducers;
Conference_Titel :
Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the
Conference_Location :
Shanghai
Print_ISBN :
0-7803-8741-4
DOI :
10.1109/IEMBS.2005.1617053
