Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Automated Measurement & Control》 2004-11
Add to Favorite Get Latest Update

Handwritten Digit Recognition Based on Wavelet Transform and ART Neural Networks

Zhang Jie~1,Kou Xueqin~2, Feng Junhong~1(1. College of management,Xi′an Univ. of Arch. & Tech.,Xi′an710055,China; 2. College of Machanical & Electronic Engineering, Xi′an Univ. of Arch. & Tech.,Xi′an,710055,China)  
Because of that wavelet transform can effectively extract the features of character construction and adaptive resonance theory (ART) neural networks has a nice learning ability, the two aspects are combined to recognize handwritten digit using wavelet transform to extract features and adaptive resonance theory (ART) neural networks for classification. The result of experiment shows high recognition rate, which indicates that the methods can effectively classify hand written digit and be put into practical use.
【Fund】: 陕西省教育厅专项基金资助项目(01JK201)
【CateGory Index】: TP391.4
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved