Glove-Based Approach to Online Signature Verification

Abstract

Utilizing the multiple degrees of freedom offered by the data glove for each finger and the hand, a novel on-line signature verification system using the Singular Value Decomposition (SVD) numerical tool for signature classification and verification is presented. The proposed technique is based on the Singular Value Decomposition in finding r singular vectors sensing the maximal energy of glove data matrix A, called principal subspace, so the effective dimensionality of A can be reduced. Having modeled the data glove signature through its r-principal subspace, signature authentication is performed by finding the angles between the different subspaces. A demonstration of the data glove is presented as an effective high-bandwidth data entry device for signature verification. This SVD-based signature verification technique is tested and its performance is shown to be able to recognize forgery signatures with a false acceptance rate of less than 1.2%.

About One Method of On-Line Signature Verification Using Radial Basis Function

“…The offered way does not deny the existing verification methods (Kamel, et al, 2008), (Impedovo, & Pirlo, 2008), (Fabregas, Faundez-Zanuy, 2009), (Miguel-Hurtado, et al, 2007), it is an additional alternative when determining the results of the signature recognition.…”

A subspace-based technique for image noise reduction

“…In subspace filtering using TDC linear estimator, the choice of reduced rank r is experimentally determined using the method outlined in section II-C and it has value of 249, 193 and 246 for the Barbara, Lena and boat respectively. The rule of selecting r is based on the conceptual relations between SVD and oriented energy [11] which stated that for Also, the Lagrange multipliers λ for the TDC estimator is experimentally determined according to the method outlined in section II-D and have the value between the range of 5 to 10. In this experiment, λ is chosen to be 7.…”

Speckle noise filtering based on signal subspace technique

“…The reduced rank model in calculating H SDC can be derived using the perturbation theorem [14] and the relationship between maximal oriented energy and the signal subspace [23], [24].…”

“…On the other hand, the eigenvalues of R Y is equal to the sum of Δ X and noise variance, v 2 n hence, Δ X can be estimated directly from (26) provided that the value of v 2 n is known. Using this relationship, the α i expression in (23) can be casted in terms of the eigenvalues of R Y as follows…”