Classification of quickbird image with mazimal mutual information feature selection and support vector machine

摘要：

This paper presents a method to select optimal feature subset from object-orientated image segmentation according to the maximal mutual information to improve classification accuracy of high spatial resolution imagery over urban area. The proposed method is a three-step classification routine that involves the integration of 1) image segmentation with eCoginition software, 2) feature selection by maximal mutual information criterion, and 3) support vector machine for classification. Experiment is conducted on Quick-Bird image in Fuzhou city. Furthermore, the proposed method with the well known feature selection methods, namely Tabu greedy search algorithm and fisher discriminate analysis, are evaluated and compared. The experiment shows that the mean error ratio significantly decreases with feature selection. It also demonstrates that the proposed maximal mutual information feature selection with support vector machine classifier significantly outperforms the classification method accompanied with eCoginition platform in terms of Z test.

关键词： mazimal mutual information feature selection object-oriented classification high spatial resolution image

作者: Wu Bo Xiong Zhu-guo Chen Yun-zhi Zhao Yin-di

作者单位: Spatial Information Research Center of Fujian Province, Fuzhou University, Fuzhou 350002, China School of Earth Science and Survey Mapping, East China University of Technology, Fuzhou 344000, Chin School of Environmental Science and Spatial Informatics, China University of Mining and Technology,

会议类型: 国际会议

会议名称: The 6th International Conference on Mining Science & Technology ICMST 2009(第六届国际矿业科学技术大会)

会议地点: 徐州

会议语种:英文

页码: 1-8

在线出版日期: 2009-10-18（万方平台首次上网日期，不代表论文的发表时间）