Online Signature Verification Based on the Hybrid HMM/ANN Model
Zhong-Hua Quan, Kunhong Liu · 2007
This paper presents a new approach based on HMM/ANN hybrid for online signature verification. The hybrid HMM/ANN model is constructed by using a type of time delay Neural Networks as local probability estimators for an HMM, where a posterior probability of the model is worked out by the Viterbi algorithm, given an observation sequence. The proposed HMM/ANN hybrid has a strong discriminant ability i.e, from a local sense, the ANN can be regarded as an efficient classifier, and from a global sense, the posterior probability is consistent with that of a Bayes classifier. Finally, the experimental results show that this approach is promising and competing.