Offline signature verification using supervised neural networks

Offline signature verification was the first approach to be applied for solving the signature verification problem for static images. It involves the discrimination of genuine and fake signatures on static images. In offline systems we have only the static image containing the signature as an input, without having any knowledge on the signing process. Some difficulties that may be come up in offline systems are related to the scanning process (noise on the image) and to the signature acquisition process where different pen tips and widths can produce different shapes. This paper presents a method of signature verification using Supervised neural networks and determine the percentage of number of times correct signature have been recognized as correct then we calculate the average performance of the Networks and A comparison among the neural networks was drawn and generalize on which of these techniques provide the better results i.e. which technique is more suitable for identifying the forged signatures.