Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Xi'an Polytechnic University》 2008-02
Add to Favorite Get Latest Update

Character recognition based on adaptive genetic neural network

WANG Xiao-dong1,XUE Hong-zhi2,MA Ying-cang1 (1.School of Science,Xi′an Polytechnic University,Xi′an 710048,China;2.School of Science,Chang′an University,Xi′an 710064,China)  
An improved algorithm has been given in order to make the robust characteristic of traditional adaptive genetic algorithm stronger during the initial evolutionary process and overcome premature convergence,then the neural network weights and threshold of BP model is adjusted by the algorithm.Finally,the new algorithm is applied to character recognition.Simulation results prove that the new algorithm has a stronger discernment than the BP algorithm.
【Fund】: 陕西省教育厅专项科研计划项目(07JK255);; 西安工程大学校管科研资助项目(2006XG37)
【CateGory Index】: TP18;TP391.43
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