Offline Handwritten Signature Identification and Verification Using Contourlet Transform

Abstract

In this paper, a new offline handwritten signature identification and verification system based on contourlet transform is proposed. Contourlet transform (CT) is used as feature extractor in proposed system. Signature image is enhanced by removing noise and then it is normalized by size. After preprocessing stage, by applying a special type of contourlet transform on signature image, related contourlet coefficients are computed and feature vector is created. Euclidean distance is used as classifier. One of the most important features of proposed system is its independency from signer's nationality. Experimental results show that proposed system has so reliable results for both Persian and English signatures.

Ähnliche Arbeiten