On-line handwriting signature verification algorithm based on DTW energy feature matching of sharp trajectory change point
基于跳变点能量的DTW匹配在线手写签名验证算法

The paper proposed an on-line handwriting signature verification algorithm as feature based on signature energy, emphasized the study of signature energy features extraction method and matching and decision-making process. Extracted the energy of sharp trajectory change point in the signature wave, by means of wavelet decomposition of signature. Then, chosen some points with most dominant energies as characteristic value. Matching the pattern character and test character with dynam- ic time warping enables the researchers to compare the distortions between them so as to obtain the criterion for identification, calculated the minimum marching distanee, got matching route. According to the experiment, the algorithm of DTW performed well in the handwriting signature verification, Resu/ts show that false rejection rate is 0 percent while false acceptance rate is 6. 86 percent for random forgery .