On-line Chinese signature verification with mixture of experts

We propose an on-line Chinese signature verification system based on mixture of experts to further improve the reliability of a signature verification system. As we know, the signature of a certain signer has some personal particular characteristics. We collect these characteristics, and classify them into several feature vectors. In our system, an individual feature vector corresponds to an expert which performs the function of signature verification. According to the particular habit of an individual signer, an individual expert with a particular feature vector plays a different role with different power to a different signer. These verification results should be weighted by a weighted controller. The function of the weighted controller works as the personal habit function. In our proposed system, there are seven verification experts with different feature vectors to make their verification decision. Based on these results, the combination unit with a weighted controller makes the final decision. The weighted controller controls the weight of the decision between the experts and the individual signer. Then, the combination of mixture results of the seven experts is attained, and a signature verification system with a personal-oriented feature decision is approached. Finally, the performance of our system is demonstrated in several experiments which show a high success rate of verification