A Robust and Invariant Complex Variable Methodology-Based Technique for Handwritten Signature Recognition

摘要

In this paper we introduce a new innovative technique for handwritten signature representation and recognition. This method differs much from other research done on signature recognition since it seeks for a unique representation of a signature. The proposed technique is based on complex variables and conformal mapping methodology. In particular, in a previous work, through a complex variable methodology and conformal mapping process, we demonstrated the ability to (a) recognize shapes, and (b) concisely represent shape boundaries using a set of polynomial coefficients derived in the mapping process. In this work we illustrate how these previous results can be applied to handwritten signature recognition. We show that the signatures classification techniques used are adapted to the feature-coefficients selected and are based on feature-coefficients similarities in combination with the minimum distance classifier. We use as measures the Euclidean distance as well as well as the covariance matrix eigen values distance. Finally, several signatures are considered including faked ones and experimental results are presented to show the power, versatility and robustness of the proposed techniques for handwritten signature recognition, and machine vision/intelligence in general.