A Fast HMM Algorithm for On-line Handwritten Character Recognition
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
An On-Line Handwriting Characters Recognition Algorithm RAV (Reparameterized Angle Variations)
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Automated signature detection from hand movement
CompSysTech '04 Proceedings of the 5th international conference on Computer systems and technologies
A Bayesian MCMC on-line signature verification
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Towards the development of haptic-based interface for teaching visually impaired arabic handwriting
Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility
Hi-index | 0.00 |
This paper proposes a new algorithm PPI (pen-position/penpressure/ pen-inclination) for on-line pen input signature verification. The algorithm considers writer's signature as a trajectory of pen-position, penpressure and pen-inclination which evolves over time, so that it is dynamic and biometric. Since the algorithm uses pen-trajectory information, it naturally needs to incorporate stroke number (number of pen-ups/pen-downs) variations as well as shape variations. The proposed scheme first generates templates from several authentic signatures of individuals. In the verification phase, the scheme computes a distance between the template and input trajectory. Care needs to be taken in computing the distance function because; (i) length of a pen input trajectory may be different from that of template even if the signature is genuine; (ii) number of strokes of a pen input trajectory may be different from that of template, i.e., the number of pen-ups/pen-downs obtained may differ from that of template even for an authentic signature. If the computed distance does not exceed a threshold value, the input signature is predicted to be genuine, otherwise it is predicted to be forgery. A preliminary experiment is performed on a database consisting of 293 genuine writings and 540 forgery writings, from 8 individuals. Average correct verification rate was 97.6 % whereas average forgery rejection rate was 98.7 %. Since no fine tuning was done, this preliminary result looks very promising.