Pen-input on-line signature verification with position, pressure, inclination trajectories

Abstract

A new algorithm is proposed for pen-input on-line signature verification incorporating pen-position, pen-pressure and peninclinations trajectories. Preliminary experimental result looks encouraging.

Automatic Signature Verification: The State of the Art

“…function is conveyed directly by the acquisition device whereas velocity and acceleration functions can be provided by both the acquisition device [121], [178] and numerically derived from position [40], [51], [346]. In recent years, pressure and force functions have been used frequently and specific devices have been developed to capture these functions directly during the signing process [46], [219], [235], [237], [300], [374]. In particular, pressure information, which can be registered with respect to various velocity bands, has been exploited for signature verification in order to take advantage of interfeature dependencies [154].…”

Signature Verification Using N-tuple Learning Machine

“…This paper proposes a new algorithm for on-line signature verification after individuality in the altitude, pressure and xy position based on feature extraction graphs [4][5] [6], then convert to binary images. Using N-tuple technique for recognition [7].…”

Nonlinear separation of signature trajectories for on-line personal authentication

“…In [1]- [5], we proposed algorithm PPI [penpositionlpen-pressureipen-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.…”

“…In our previous work [I 1- [5], genuine signatures were separated from forgery signatures in a linear manner. This paper attempts to perform the nonlinear separation.…”

“…Table3.1 Database 1 Signatures for Learning I Signatures for Testing I Table3.2 shows verification error rates as a function of h (the number of hidden layer). FAR represents False Acceptance Rate and FRR represents False Rejection Rate.Since our previous scheme[I]-[5] contains a free parameter c to be chosen, direct comparison is impossible, however, the minimum FAR 1.08%, and the minimum FRR 1.00%, of the proposed algorithm are very encouraging.…”