Persian off-line signature recognition with structural and rotation invariant features using by one-against-all SVMclassifier

The problem of automatic signature recognition has received little attention incomparison with the problem of signature verification, despite its potentialapplications for many business processes and can be used effectively in paperlessoffice projects. This paper presents model-based off-line signature recognition withrotation invariant features. Non-linear rotation of signature patterns is one of themajor difficulties to be solved in this problem. The proposed system is designedbased on support vector machines (SVM) classifier technique and rotation invariantstructure feature to tackle the problem. Our designed system consists of threestages: the first is preprocessing stage, the second is feature extraction stage and thelast is SVM classifier stage. Experimental results demonstrated that the proposedmethods were effective to improve recognition accuracy.

کلیدواژه ها:

Persian off-line signature recognition ، Rotation invariant ، structural feature ، SVM