Query Learning Method for Character Recognition Methods Using Genetic Algorithm
H. SAKANO · IEICE Transactions on Information and Systems · 2005
We propose a learning method combining query learning and a we previously developed. Query learning is a useful technique for high-accuracy, high-speed learning and reduction of training sample size. However, it has not been applied to practical optical character readers (OCRs) because human beings cannot recognize queries as character images in the feature space used in practical OCR devices. We previously proposed a character image reconstruction method using a genetic algorithm. This method is applied as a translator from feature space for query learning of character recognition. The results of an experiment with hand-written numeral recognition show the possibility of training sample size reduction.