OFFLINE FORGERY DETECTION OF HANDWRITTEN SIGNATURE USING GAUSSIAN EMPIRICAL RULE

Abstract

Signature authentication is most widely used in verifying a person’s identity. In this paper Global and
Geometric features are discussed. Before extracting the features, preprocessing of a scanned image is necessary to
isolate the region of interest part of a signature and to remove any spurious noise present. The system is trained initially
with the data-set of signatures obtained from those individuals whose signatures are to be authenticated by the system.
All the features are computed for training samples of signature. There are some variation itself in features of genuine set
of signatures. If testing signature sample satisfies the Gaussian empirical rule it is authenticated as original signature
otherwise a forged one.