Automatic Aurora Images Classification Algorithm Based on Separated Texture

摘要：

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 exhibited the classification accuracy improved by 10％, of which, the SVM with linear kernel is much faster and is therefore suitable for massive data processing.

作者: Rong Fu Jie Li Xinbo Gao Yongjun Jian

作者单位: School of Electronic Engineering,Xidian University School of Computer Science,Xian Polytechnic Univ School of Electronic Engineering,Xidian University,Xian China Video & Image Processing System (VIPS) Lab School of Electronic Engineering,Xidian University

会议类型: 国际会议

会议名称: 2009 IEEE International Conference on Robotics and Biomimetics(2009 IEEE 机器人与仿生技术国际会议 ROBIO 2009)

会议地点: 桂林

会议语种:英文

页码: 1331-1335

在线出版日期: 2009-12-19（万方平台首次上网日期，不代表论文的发表时间）