An Integrated Approach for Offline Signature Classification Using Ann

A great deal of work has been done in the area of off-line signature verification over the last two decades. Offline systems are of interest in scenarios where only hard copies of signatures are available, especially where a large number of documents need to be authenticated. This paper is inspired by, amongst other things, the potential financial benefits that the automatic clearing of cheques will have for the banking industry. The purpose of this research is to develop a novel, accurate and efficient off-line signature verification system. In this proposed system we are collecting the sample from 480 people genuine and fake signature and for feature extraction use the DCT and IDCT technique. After getting the feature for training and testing we the neural network.