Signature envelope curvature descriptor for offline signature verification

This paper presents an algorithm for feature descriptor extraction of signature using signature envelope curvature sequences which are rotation invariant. The envelope curvature reflects both the direction change pattern of the envelope sequence and smoothness of the envelope that are usually employed for signature verification by human experts. A polygon matching technique is applied to eliminate the shift effect which results from the arbitrary start point selection for calculation of the proposed envelope curvature features. To make the method robust to be size invariant, a normalization process is done with additional benefit of feature dimension reduction. Finally, experimental results show comparable performance of the proposed method aiming at simple and skill forgery detection for offline signature verification.