Abstract
AbstractIn our previous research, neuro-template matching method1 was proposed for currency recognition. In this paper, neuro-template with sigmoid as activation function is applied in the individual recognition system with writing pressure, and the experiment shows that this method is effective on the known pattern recognition, however it suffers from poor rejection capability for counterfeit signatures. To solve previous problem, Gaussian function is proposed as activation function of neuro-template and optimal parameters are customized for neuro-template of each registrant. The experiment shows that the customized neuro-template with Gaussian activation function is seemed to be very effective on improving the rejection capability of the system for counterfeit signatures with ensuring the recognition capability satisfied.KeywordsActivation FunctionGaussian FunctionSigmoid FunctionNeural Network SystemRecognition CapabilityThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call