ABSTRACT

In this paper we present an off-line signature verification and recognition system based on a combination of features extracted such as blob features, average of radon transform, fusion of grid and global features using average and clustering technique. The system is trained using a database of signatures. For each person, a feature vector is obtained from a set of his/her genuine samples using the features that were extracted. The signature is then used as a template which is used to verify a claimed signature. We use the Euclidean distance in the feature space to obtain measure of similarity between template signature and claimed signature. We have discussed four methods and combined the results as per observations based on far, frr and gar.