Discussion of reliability criterion for US dollar classification by LVQ

A bill money classification has become automated and it is important that the classifier has higher accuracy. Generally, the accuracy of classification is represented as the recognition rate of sample data. However, when classifying bill money, we must evaluate the accuracy more strictly. For pattern recognition a neural network (NN) is studied and its ability is highly estimated. Among NNs a competitive NN has a simple structure and can be analyzed by the relation between the inputs and the outputs more easily than a layered NN based on the backpropagation method. Because of this, we use a competitive NN for bill money classification and use the learning vector quantization (LVQ) method for training the NN. We propose a reliability criterion based on a probability distribution for the classification by the LVQ method. Then we classify US dollars by the LVQ and apply the reliability criterion to the classification. We show that the proposed method of bill money classification has higher accuracy.