Reject Mechanisms for Massively Parallel Neural Network Character RecognitionSystems

摘要

Two reject mechanisms are compared using a massively parallel characterrecognition system implemented at the National Institute of Standards and Technology (NIST). The recognition system was designed to study the feasibility of automatically recognizing hand-printed text in a loosely constrained environment. The first method is a simple scalar threshold on the output activation of the winning neurode from the character classifer network. The second method uses an additional neural network trained on all outputs from the character classifier network to accept or reject assigned classifications. The neural network rejection method was expected to perform with greater accuracy than the scalar threshold method, but this was not supported by the test results. The scalar threshold method, even though arbitrary, is shown to be a viable reject mechanism for use with neural network character classifiers. Upon studying the performance of the neural network rejection method, analyses show that the two neural networks, the character classifier network and the rejection network, perform very similarly. This can be explained by the strong non-linear function of the character classifier network which effectively removes most of the correlation between character accuracy and all activations other than the winning activation. This suggests that any effective rejection network must receive information from the system which has not been filtered through the non-linear classifier.