Chinese Signature Identification Based on Dynamic Studying System

The basic principle of online Chinese signature identification is to compare one´s signature characteristic value with those in the appointed pattern librarypsilas so that the signature to be identified is classified as either authentic or forged. In order to form a stable and effective pattern library, a new method is proposed based on the fact that the Fisher distinction criterion function is a generalized Rayleigh quotient in essence. The extremum properties of generalized Rayleigh quotient are analyzed and a new method of forming pattern library is given based on dynamic studying system, which can be dynamically adapted in runtime to model the variation of signature, and then a proper classifier is developed which can be more effective and robust than the traditional Euclid Distance. The simulation results also show that this method has better stability and reliability.