| 基于形态学成分分析的静态极光图像分类算法 |
| |
| 引用本文： | 付蓉,李洁,高新波.基于形态学成分分析的静态极光图像分类算法[J].光子学报,2014,39(6):1034-1039. |
| |
| 作者姓名： | 付蓉 李洁 高新波 |
| |
| 作者单位： | (1 西安电子科技大学 电子工程学院,西安710071)(2 西安工程大学 计算机科学学院,西安710048) |
| |
| 基金项目： | 国家自然科学基金（60702061、60402038）和中国气象局公益性行业（气象）科研专项经费(GYHY200706043)资助 |
| |
| 摘 要： | 为了解决海量极光图像手工分类效率低下的问题,提出一种静态极光图像自动分类系统,使用形态学成分分析将极光纹理从复杂背景中分离出来,从纹理中提取特征并利用支持向量机进行分类.实验结果表明:该算法分类正确率较之于传统方法均提高约10%,当分类器支持向量机+线性核函数时,分类速度最快,最适合于海量数据的处理.
|
| 关 键 词： | 图像分类 形态学成分分析 支持向量机 日侧冕状极光 |
| 收稿时间： | 2008-12-29 |
Image classification|Morphological Component Analysis(MCA)|Support Vector Machine(SVM)|Diurnal corona aurora |
| |
| FU Rong,LI Jie,GAO Xin-Bo.Image classification|Morphological Component Analysis(MCA)|Support Vector Machine(SVM)|Diurnal corona aurora[J].Acta Photonica Sinica,2014,39(6):1034-1039. |
| |
| Authors: | FU Rong LI Jie GAO Xin-Bo |
| |
| Institution: | (1 School of Electronic Engineering,Xidian University,Xi′an 710071,China)(2 School of Computer Science,Xi′an Polytechnic University,Xi′an 710048,China) |
| |
| Abstract: | In order to resolve the problem incurred by low efficient manual classification of tremendous aurora images,an automatic aurora images classification system for huge dataset application is proposed.First,static aurora images are decomposed into texture part and cartoon part with a method called Morphological Component Analysis (MCA).Then features extracted from texture part are classified by three classification methods:nearest neighbor (NN),Support Vector Machine (SVM) with RBF kernel and SVM with linear kernel.The experiment results exhibit that the classification accuracy improved by 10%,of which,the SVM with linear kernel is much faster and is therefore suitable for massive data processing. |
| |
| Keywords: | |
|
| 点击此处可从《光子学报》浏览原始摘要信息 |
| 点击此处可从《光子学报》下载免费的PDF全文 |
|
