Chaotic Neural Network for Biometric Pattern Recognition

[摘要] Biometric pattern recognition emerged as one of the predominant research directions in modern security systems. Itplays a crucial rolein authentication of bothreal-worldand virtualrealityentitiestoallowsystemtomakeaninformed decision on grantingaccess privileges or providing specialized services. The major issues tackledby the researchers are arising from the ever-growing demandson precision and performance of securitysystems andatthe sametimeincreasingcomplexityof dataand/or behavioral patterns to be recognized. In this paper, weproposetodealwithbothissuesbyintroducingthenew approachtobiometric patternrecognition, based onchaotic neural network(CNN). Theproposedmethodallows learning the complex data patterns easily while concentrating on the most importantforcorrectauthenticationfeaturesandemploysa unique method to train different classifiers based on each feature set. The aggregation result depicts the final decision over the recognized identity.In order to train accurate set of classifiers, the subspace clustering method has been used to overcome the problem of high dimensionality of the feature space. The experimental results show the superior performance of the proposed method.

[学科分类] 人工智能