On-Line Handwriting Signature Recognition Based on Wavelet Energy Feature Matching

An on-line handwriting signature identity recognition algorithm based on wavelet analysis is proposed. Online signature recognition includes data acquisition, preprocessing, feature extraction, and matching and decision making process. The study of signature energy feature extraction method is emphasized. The energy of sharp trajectory change point in the signature wave is extracted, by means of Daubechies wavelet decomposition of signature signal. Then, all the energies are arranged in descending order and the first M most dominant energies are chosen as feature vector. A new algorithm of classification is introduced. Experiment findings show that false acceptance rate is 8.5 percent while false rejection rate is 0 percent for random forgery