Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Microcomputer Information》 2007-27
Add to Favorite Get Latest Update

Research on B-Scan Ultrasonic Image Recognition of Fatty Liver Based on Artificial Neural Network

QUAN Wei-wei1, WU Bin2, Zhang Ji-hua3(School of Information Engineering, SWUST, Mianyang,Sichuan 621002,China)Quan Weiwei(School of Information Engineering, SWUST, Mianyang,Sichuan 621002,China)Wu Bin(Department of function, Petroleum hospital of the northChina, Hebei 062550,China)Zhang Jihua  
A BP algorithm is proposed to recognize the B-scan ultrasonic image of fatty liver. It introduces the preprocessing the fattyliver’s image and the extraction of the feature. The discussion is emphasized on the design of BP network’s input and output layer.Also, the problem of determining the number of hidden layer’s neural nodes is discussed. The result shows that BP has robustadaptability and it shows that BP can be applied to the identification of B-scan ultrasonic images to get a better effect.
【Fund】: 四川省应用基础项目---基于知识的优化控制研究(01GY051-37)
【CateGory Index】: TP391.41;TP18
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