2009 · 17 citations · 12 references
ComputingComputer ScienceAuthenticationFeature EngineeringKnowledge RepresentationDigital SignaturesPattern RecognitionSymbolic RepresentationBiometric SignaturesCentroid ComputationCentroid EstimationSignature AnalysisSignature VerificationSymbolic Feature Engineering
In this paper, we propose a new approach for symbolic representation of off-line signatures useful for verification. The proposed approach is based on relative orientations of geometric centroids of split portions of signatures. Centroid orientation features of off-line signatures are used to form an interval valued symbolic feature vector for representing signatures. A method of off-line signature verification based on the symbolic representation is presented. We investigate the feasibility of the proposed representation scheme for signature verification on a MCYT_signature database. Unlike other signature verification methods, the proposed method is simple and efficient. Several experiments are conducted to demonstrate the efficacy of the proposed scheme.
12