| 一种图片分类的序列构造神经网络方法 |
| |
| 引用本文： | 王仁武,陈家训.一种图片分类的序列构造神经网络方法[J].计算机工程与应用,2007,43(31):172-174. |
| |
| 作者姓名： | 王仁武 陈家训 |
| |
| 作者单位： | 东华大学信息学院，东华大学信息学院 上海200051华东师范大学信息学系，上海200062，上海200051 |
| |
| 摘 要： | 针对图片数据的分类问题,从动态构造网络的思想出发,讨论了序列构造神经网络的基本方法,并且把其应用于图片分类中,最后给出标准测试集的分类测试结果,并对其进行了比对、分析和讨论,实验结果表明此方法适合多维数据分析,取得了满意的效果。
|
| 关 键 词： | 动态构造 图片分类 神经网络 |
| 文章编号： | 1002-8331（2007）31-0172-03 |
| 修稿时间： | 2007-07 |
Method of classification for images based on SCNN |
| |
| WANG Ren-wu,CHEN Jia-xun.Method of classification for images based on SCNN[J].Computer Engineering and Applications,2007,43(31):172-174. |
| |
| Authors: | WANG Ren-wu CHEN Jia-xun |
| |
| Affiliation: | 1.College of Information,Donghua University,Shanghai 200051,China ;2.Department of Information,East China Normal University, Shanghai 200062,China |
| |
| Abstract: | To the problems of image classification,Sequence Constructive Neural Network(SCNN) method is discussed using the idea of dynamic creation of neural network and its application in the image classification.Benchmark tests are launched in the paper,and also give its compares and analysis.From the experiments,the method of SCNN is more suitable for multi-dimension data analysis and can give satisfied results. |
| |
| Keywords: | dynamic creation image classification neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
