Off-line signature verification using curve fitting algorithm with neural networks

As signature is widely used as a means of personal verification, it is necessary for an automatic verification system. Offline and Online are two methods of verification based on the application. Online systems use dynamic information of a signature captured at the time the signature is made. Offline systems work on the scanned image of a signature. Processing Off-line is complex due to the absence of stable dynamic characteristics and also due to highly stylish and unconventional writing styles. A simple and a reliable system has to be designed which should detect various types of forgeries. Hence this paper proposes architecture for off-line signature verification. Our approach makes use of runtime signature instead of scanned images for recognition. This Offline verification of signatures uses a set of shape based geometric features and more importantly focuses on the distance based parameters such as the continuity of the signature and matching of the curves of the signatures generated by the critical points of the respective signature by analyzing the polynomial equation. Curve fitting and the analyzing of polynomial equations is one of the least explored topics till date but yet very efficient and hence we have implement this novel technique.