Trainable pattern classifier using a computer-generated hologram

研究成果: 雜誌貢獻期刊論文同行評審

摘要

A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.

原文英語
頁(從 - 到)1910-1913
頁數4
期刊Japanese Journal of Applied Physics
33
發行號4R
DOIs
出版狀態已發佈 - 1994 4月
對外發佈

ASJC Scopus subject areas

  • 工程 (全部)
  • 物理與天文學 (全部)

指紋

深入研究「Trainable pattern classifier using a computer-generated hologram」主題。共同形成了獨特的指紋。

引用此