In today's world security is very important. An integral part of security is authentication as based on a person's identity he is authorized to certain privileges. There are many means for authentication, and signature is one among them. Since decades, signatures are considered as a means of authentication and 'seal of approval'. An important advantage of the signature verification compared with others is its long tradition in many commercial fields such as e-business, which includes online

more »

... ing transaction, electronic payments, access control and so on. In banks whenever a person wants to carry out ay financial transaction the signature is used to verify the identity of the person. To date signatures verification is done manually in banks where a person manually verifies the signature on the cheque with specimen signature. But this method is not accurate as naked eye cannot detect forgeries. Our proposed system deals with computerized signature verification in banking application. This is how signature verification system originated. Verification of signatures can be done on-line or off-line depending upon the application. Where the signature is captured and presented to the user in an image format. Signatures are verified based on parameters extracted from the signature using various techniques. The signature features, to be tested, are fed to the trained neural network to find whether the signature is genuine or a forged one.