On-line signature verification using local shape analysis
Mingfu Zou, Jianjun Tong, Changping Liu, Zhengliang Lou · 2004
This paper presents a novel approach to the on-line signature verification using local shape analysis. First, segment the input signature into several segments using HMM (hidden Markov model). Then, combine two adjacent segments to form a long segment and get its spectral and tremor information using FFT (fast Fourier transformation). At last, accept it or reject it based on the similarity between the spectral and its prototype. In addition, we proposed a novel initialization algorithm to avoid the local optimal of the HMM's re-estimation and a novel algorithm to avoid losing the important information at cusps in preprocessing. Combining the local shape analysis with the local time-based comparison, we get promising experimental results.