Fusion of global and local information for an on-line Signature Verification system

In this paper, an on-line signature verification system exploiting local and global information using two-stage fusion is presented. At the first stage, global information is extracted as 13-dimensional vector and recognized by majority classifiers, and then local information is extracted as time functions of various dynamic properties and recognized by BP neural network classifier. By fusing global and local information and introducing an enhanced dynamic time warping algorithm and a normalized feature measure, our method obtained an average EER of 4.02% on public database SVC2004 (first signature verification competition 2004) Task2 compared to 6.90% the first place at SVC2004.