Query Learning Method for Character Recognition Methods Using Genetic Algorithm(<Special Section>Image Recognition and Understanding)

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a learning method combining query learning and a "genetic translator" 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.

• 2005-10-01

著者

• Sakano Hitoshi

  Ntt Data Corporation

関連論文

• Query Learning Method for Character Recognition Methods Using Genetic Algorithm(Image Recognition and Understanding)
• A Nonlinear Principal Component Analysis of Image Data(Image Recognition and Understanding)

スポンサーリンク