| 超声肝图像SOFM网络识别方法 |
| |
| 引用本文： | 陈菲.超声肝图像SOFM网络识别方法[J].西南科技大学学报,2007,22(2):40-43. |
| |
| 作者姓名： | 陈菲 |
| |
| 作者单位： | 西南科技大学计算机科学与技术学院,四川绵阳,621010 |
| |
| 基金项目： | 基金项目：国家级火炬计划项目（编号：2004EB011224）. |
| |
| 摘 要： | 通过基于空间灰度独立矩阵的特征提取方法,采用自组织特征映射神经网络对正常肝脏、肝硬化和肝癌三类肝脏超声图像进行分类识别。实验结果表明神经网络分类器对3种肝脏超声图像的分类可以达到87%的正确率,其结果对实际辅助诊断提供了理论基础。
|
| 关 键 词： | 自组织特征映射 神经网络 空间灰度独立矩阵 图像识别 |
| 文章编号： | 1671-8755（2007）02-0040-04 |
| 修稿时间： | 2007-03-05 |
SOFM Network Identification for Ultrasonic Liver Images |
| |
| CHEN Fei.SOFM Network Identification for Ultrasonic Liver Images[J].Journal of Southwest University of Science and Technology,2007,22(2):40-43. |
| |
| Authors: | CHEN Fei |
| |
| Institution: | School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, Siehuan, China |
| |
| Abstract: | A classification algorithm of ultrasonic liver images is studied in Self-organizing Feature Map.The algorithm is based on the spatial gray-level dependence matrices to classify three sets of ultrasonic liver images-normal liver,cirrhosis and hepatoma are successfully classified.The result shows that the NN classifier produces about 87% correct classification and the study provides the theoretic base for aided-diagnosis. |
| |
| Keywords: | self-organizing feature map neural network spatial gray-level dependence matrices image recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
