Signature Verification through Pattern Recognition

The signature is being used as a personal authentication this fact forces the need for an automatic verification system. The verification can be done either Offline or Online based on the application that is to be prepared. The Online systems use dynamic characteristics of a signature captured at the time the signature is made. While Offline systems work on the scanned image of a signature.[4[We have worked on the Offline Verification of signatures using a set of shape based geometric characteristics. Features that are used are Baseline Slant Angle, Aspect Ratio, Normalized Area, Center of Gravity, number of edge points, number of cross points, and the Slope of the line joining the Centers of Gravity of two halves of a signature scanned image. Pre-processing of a scanned image is necessary to differentiate the signature part and to remove any spurious noise present, before extracting the features. [4] The system is initially trained using a database of signatures acquired from those individuals whose signatures have to be authenticated by the system. For each subject a average signature is obtained integrating the above features derived from a set of his/her genuine sample signatures. This average signature acts as the basis for verification against a claimed test signature. Euclidian distance in the feature space between the claimed signature and the template serves as a measure of similarity between the two. If this distance is less than a pre-defined threshold (corresponding to minimum acceptable degree of similarity), the test signature is verified to be that of the claimed subject else detected as a forgery.[4] The details of pre-processing as well as the features depicted above are described in the report along with the implementation details and simulation results.[4