Signature Recognition and Verification Using Machine Learning Softmax Regression Model

Abstract

In today s world forgery of signature is very widely increased. There are many ‟ ‟ sophisticated scientific techniques to identify a correct signature. As signatures are widely accepted biometric for authentication and identification of a person because every person has a distinct signature with its specific behavioural property, so it is very much necessary to prove the authenticity of signature itself. A huge increase in forgery cases relative to signatures induced a need of Signature recognition system. However human signatures can be handled as an image and recognized using computer vision and neural network techniques. In this paper we have taken a set of trained images and stored their features in a database and to test an unknown image we compare the features and calculating the matching factors. We have considered 70 % as threshold for human signature recognition. Regarding creation of recognizer we gave considered HARRIS and SUFR Features. efficient “Signature Verification System.