An Accurate Method of Measuring Similarities for Chinese Signature Verification System Using Fourier Descriptors

Abstract

In this study, we present a novel approach to measure the similarities for an on-line Chinese signature verification system. The proposed system is comprised of two stages, namely, the learning stage and the verification stage. The former generates all the reference signatures for the users, and the latter calclulates the similarities between the test signature and the corresponding reference signature. A two-step matching process is proposed including the coarse matching process and the fine matching process. The method developed in [11] is adopted in this study to accomplish the coarse matching process. However, the similarity between the test and reference signatures obtained by the first step is not accurate enough. To achieve a better resuly, the method developed in [12] is modified in this study to measure the similarity for the two signatures by transforming the corresponding signature strokes into the frequency domain for futher minor adjustment. The experimental results reveal the practicavility of the proposed methods.