Signature Verification Using Support Vector Machine (SVM)
R. Krishna Kumar · International Journal of Scientific Research and Management (IJSRM) · 2017
Automated signature verification has many applications in our daily life like Bank-cheque processing,document authentication, ATM access etc. Handwritten signatures have proved to be important inauthenticating a person's identity, who is signing the document. In this paper we present an off-linesignature verification and recognition system using the global, directional and grid features of signatures.Support vector machine (SVM) was used to verify and classify the signatures. As there are unique andimportant variations in the feature elements of each signature, so in order to match a particular signaturewith the database, the structural parameters of the signatures along with the local variations in thesignature characteristics are used. The artificial neural networks are trained by these characteristic. Thesystem uses the features extracted from the signatures such as centroid, height – width ratio, total area,first and second order derivatives, quadrant areas etc. After the verification of the signature the anglefeatures are used in fuzzy logic based system for forgery detection and the performance is increasesapproximately (80%) when using SVM as a classifier