Online Signature Recognition Using Matlab

Abstract: Signature is a behavioral trait of an individual and forms a special class of handwriting in which legible letters or words may not be exhibited. The purpose of this paper is to design a new system to make the verification of signatures size and angle invariant for cheque system. The invariance can be achieved by scaling and rotational manipulations on the target image. That is the number of crests, toughs and curves remains the same irrespective of the size and orientation of the image. The ratio between consecutive crests and troughs there by remain the same and hence can be used to determine the genuineness of a signature. This system will be used in financial and business to automatic signature verification. It also includes the verification of the account number and amount on the cheque using OCR (Optical Character Recognition) and finds out if the cheque is cleared or bounced.

Keywords: image processing, OCR; Feature extraction, Segmentation, Dilation, Thinning.