VERIFICATION OF OFFLINE SIGNATURE USING MACHINE LEARNING

Abstract

Every person has a distinctive signature which is primarily used for personal identification and to confirm the authenticity of significant papers or legal transactions. The process of implementing offline or online signature verification will depend on the application. Online systems make advantage of dynamic data from a signature which is recorded while signing. Offline systems utilize a signature's scanned image for operation. Initially system is trained using a database of signatures gathered from individuals whose signatures it must authenticate. The lack of sufficient data for testing is the main issue with signature verification. High accuracy must be used in the development of signature security. In this paper, Offline signature verification that makes use of grid-based extraction of features using ML and CNN have been introduced.