Cross-validation for graph matching based Offline Signature Verification

Biometric is an authentication system that identifies a person depending on his physiological or behavioral traits. Signature verification is a socially accepted biometric method and is widely used for banking transactions. In this paper, we propose Cross-validation for Graph Matching based Offline Signature Verification (CGMOSV) algorithm. Database signatures are preprocessed in which signature extraction method is used to obtain high resolution for smaller normalization box. The dissimilarity measure between two signatures in the database is determined by (i) constructing a bipartite graph G, (ii) obtaining complete matching in G and (iii) finding minimum Euclidean distance by Hungarian method. We use Cross-validation principle to select reference signatures from which an optimum decision threshold value is determined. The given test signature is pre-processed and a test feature is extracted from it, which is then compared with the threshold value to authenticate the test signature. It is observed that our algorithm gives better Equal Error Rate (EER) for skilled forgeries and random forgeries compared to the existing algorithm.