ACCESS CONTROL BY FACE RECOGNITION USING NEURAL NETWORKS AND NEGATIVE EXAMPLES
Dmitry Bryliuk, В. В. Старовойтов · 2002
A Multilayer Perceptron Neural Network (NN) is considered for access control based on face image recognition. We studied robustness of NN classifiers with respect to the False Acceptance and False Rejection errors. A new thresholding approach for rejection of unauthorized persons is proposed. Ensembles of NN with different architectures were studied too. Advantages of the ensembles are shown, and the best architecture parameters are given. The usage of negative examples was explored. We have shown that by using negative examples we can improve performance for access control task. The explored NN architectures may be used in real-time applications.