Program for signature recognition


There exist a number of biometrics methods today e.g. Signatures, Fingerprints, Iris etc. There is considerable interest in authentication based on handwritten signature verification system as it is the cheapest way to authenticate the person. Fingerprints and Iris verification require the installation of costly equipments and hence can not be used at day to day places like Banks etc. As because Forensic experts can not be employed at every place, there has been considerable effort towards developing algorithms that could verify and authenticate the individual’s identity . Many times the signatures are not even readable by human beings. Therefore a signature is treated as an image carrying a certain pattern of pixels that pertains to a specific individual. Signature Verification Problem therefore is concerned with determining whether a particular signature truly belongs to a person or not.

Signatures are a special case of handwriting in which special characters and flourishes are viable. Signature Verification is a difficult pattern recognition problem as because no two genuine signatures of a person are precisely the same. Its difficulty also stems from the fact that skilled forgeries follow the genuine pattern unlike fingerprints or irises where fingerprints or irises from two different persons vary widely. Ideally interpersonal variations should be much more than the intrapersonal variations. Therefore it is very important to identify and extract those features which minimize intrapersonal variation and maximize interpersonal variations. There are two approaches to signature verification, online and offline differentiated by the way data is acquired. In offline case signature is obtained on a piece of paper and later scanned. While in online case signature is obtained on an electronic tablet and pen. Obviously dynamic information like speed, pressure is lost in offline case unlike online case.