Title :
Classification of the Italian Liras using the LVQ method
Author :
Omatu, Sigeru ; Kosaka, Toshihisa ; Teranisi, Masaru
Author_Institution :
Osaka Prefectural Univ., Sakai, Japan
Abstract :
For the pattern classification problems the neuro-pattern recognition which is the pattern recognition based on the neural network approach has been paid an attention since it can classify various patterns like human beings. In this paper, we adopt the learning vector quantization(LVQ) method to classify the various money. The reasons to use the LVQ are that it can process the unsupervised classification and treat many input data with small computational burdens. We will construct the LVQ network to classify the Italian Liras. Compared with a conventional pattern matching technique, which has been adopted as a classification method, the proposed method has shown excellent classification results.
Keywords :
bank data processing; neural nets; pattern classification; unsupervised learning; vector quantisation; Italian Liras classification; LVQ method; LVQ network; bank notes; computational burdens; learning vector quantization; money classification; neural network; pattern classification; unsupervised classification; Biological neural networks; Educational institutions; Humans; Neurons; Office automation; Pattern classification; Pattern matching; Pattern recognition; Pixel; Size measurement;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223752