A genetic sparse distributed memory approach to the application of handwritten character recognition

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 期刊論文 > Item 987654321/29191

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/29191

題名:	A genetic sparse distributed memory approach to the application of handwritten character recognition
作者:	Fan,KC;Wang,YK
貢獻者:	資訊工程研究所
日期:	1997
上傳時間:	2010-06-29 20:15:57 (UTC+8)
出版者:	中央大學
摘要:	Kanerva's Sparse Distributed Memory (SDM) is one of the self-organizing neural networks that mimic closely the psychological behavior of the human brain. In this paper, a Genetic Sparse Distributed Memory (GSDM) model that combines SDM with genetic algorithms is proposed. The proposed GSDM model not only maintains the advantages of both SDM and genetic algorithms, but also has higher memory utilization to improve the recognition rate. Its effective performance is also verified by application to Optical Character Recognition (OCR). Experimental results reveal the feasibility and validity of the proposed model. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.
關聯:	PATTERN RECOGNITION
顯示於類別:	[資訊工程研究所] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	494	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing