An Off-line Signature Verification System Based on Fusion of Local and Global Information

An off-line signature verification system based on fusion of two machine experts is presented. One of the experts is based on global image analysis and a statistical distance measure while the second one is based on local image analysis and Hidden Markov Models. Experimental results are given on a subcorpus of the large MCYT signature database for random and skilled forgeries. It is shown experimentally that the machine expert based on local information outperforms the system based on global analysis in all reported cases. The two proposed systems are also shown to give complementary recognition information which is exploited with a simple fusion strategy based on the sum rule.