Signature recognition and verification with ANN
Cemil Öz, Fikret Erçal, Zafer Demir · 2003
In this paper, we present an off-line signature recognition and verification system which is based on moment invariant method and ANN. Two separate neural networks are designed; one for signature recognition, and another for verification (i.e. for detecting forgery). Both networks use a four-step process. First step is to separate the signature from its background. Second step performs normalization and digitization of the original signature. Moment invariant vectors are obtained in the third step. And the last step implements signature recognition and verification.