Handwritten signatures are considered as the most natural method of authenticating a person’s identity as compared to other biometric and cryptographic forms of authentication. The learning process inherent in Neural Networks can be applied to the process of verifying handwritten signatures that are electronically captured via a stylus. This work presents a method for verifying handwritten signatures by using Neural Networks architecture. Various features of signature such as height, length, slant, moment etc. are extracted and used to train the Network.