[1]张秀英,冯学智,刘伟.基于多分类器结合的IKONOS影像城市植被类型识别[J].东南大学学报(自然科学版),2007,37(3):399-403.[doi:10.3969/j.issn.1001-0505.2007.03.009]
 Zhang Xiuying,Feng Xuezhi,Liu Wei.Urban vegetation categories recognition by multiple classifier system from IKONOS imagery[J].Journal of Southeast University (Natural Science Edition),2007,37(3):399-403.[doi:10.3969/j.issn.1001-0505.2007.03.009]
点击复制

基于多分类器结合的IKONOS影像城市植被类型识别()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
37
期数:
2007年第3期
页码:
399-403
栏目:
图像处理
出版日期:
2007-05-20

文章信息/Info

Title:
Urban vegetation categories recognition by multiple classifier system from IKONOS imagery
作者:
张秀英12 冯学智2 刘伟23
1 浙江大学农业遥感与信息技术应用研究所, 杭州 310029; 2 南京大学地理与海洋科学学院, 南京 210093; 3 安徽省黄山市国土资源局, 黄山 245011
Author(s):
Zhang Xiuying12 Feng Xuezhi2 Liu Wei23
1 Institute of Remote Sensing and Information System Application, Zhejiang University, Hangzhou 310029, China
2 School of Geographic and Oceanographic Sciences, Nanjing University, Nanjing 210093, China
3 Anhui Huangshan Bureau of Land and Resources, Huangshan 245011, China
关键词:
城市植被 投票规则 多分类器
Keywords:
urban vegetation plurality voting rules multi-classifier systems
分类号:
TP751.1
DOI:
10.3969/j.issn.1001-0505.2007.03.009
摘要:
采用多分类器结合的方法对城市植被进行分类.首先,以分割获得的城市植被分布斑块为处理基元,在不同特征空间中采集不同的样本,通过ISODATA、马氏距离、最大似然、人工神经网络和专家系统法进行分类,并计算各分类结果的关联程度和各植被类型识别的先验概率; 然后利用专家投票的大多数规则对分类结果组合,未分类的对象按照先验识别概率最高的结果归类.精度评价表明:多分类器结合方法显著提高了信息识别的能力; 采用多分类器结合的方法比单个分类器获得的最高分类精度提高5.5%,Kappa系数提高7.4%; Z统计值均为负,且均通过95%的置信水平检验.
Abstract:
In order to improve urban vegetation classification results, the method of multi-classifier systems was employed. Firstly, taking the “objects” from segmentation as the classification units, five kinds of classifiers of ISODATA(self-organizing data analysis techniques algorithm), Mahalanobis distance, maximum likelihood, neural network and expert system were used to identify vegetation types using different samples in different feature spaces. Secondly, the Q statistic representing relationships between a pair of classifiers and the pre-probability of all categories of vegetation for the five classifier results were calculated. Thirdly, the plurality voting rule was used to combine the five vegetation maps, and the unclassified “objects” was estimated by the category with the highest pre-probability. The results of accuracy assessment show that the vegetation map by plurality voting rules has higher total accuracy and Kappa coefficient, which are respectively 5.5% and 7.4% higher than the solo classifier with the highest accuracy. Z statistic values also show that the method of plurality voting rules greatly improves the classification results.

参考文献/References:

[1] Kittler J. Improving recognition rates by classifier combination:a theoretical framework [C] //Progress in Handwriting Recognition.Singapore:World Scientific Publishing,1997:231-248.
[2] Hull J J,Commike A,Ho T K.Multiple algorithms for handwritten character recognition [C] //Proceedings of International Workshop Frontiers in Handwriting Recognition.Montreal,Canada,1990:117-129.
[3] Xu L,Krzyzak A,Suen C Y.Methods of combining multiple classifiers and their applications to handwriting recognition [J]. IEEE Transaction on Systems,Man,Cybemetics,1992,22(3):418-435.
[4] Lin Xiaofan,Yacoub Sherif,Burns John,et al.Performance analysis of pattern classifier combination by plurality voting[J]. Pattern Recognition Letter,2003,24(12):1959-1969.
[5] Lam L,Suen C Y.Application of majority voting to pattern recognition:an analysis of the behavior and performance [J].IEEE Trans Systems Man Cybernet,1997,27(5):553-567.
[6] Kuncheva L I.Lombining classifiers by clustering,selection and decision templates 2000[EB/OL].[2006-06].http://www.bangor.ac.uk/~masooa/publications.html.
[7] 杨丽英,覃征,张选平.分类器模拟算法及其应用[J].西安交通大学学报,2005,39(12):1311-1314.
  Yang Liying,Qin Zheng,Zhang Xuanping.Classifier simulation algorithm and its applications[J].Journal of Xi’an Jiaotong University,2005,39(12):1311-1314.(in Chinese)
[8] 孙怀江,胡钟山,杨靖宇,等.基于证据理论的多分类器融合方法研究[J].计算机学报,2001,24(3):231-235.
  Sun Huaijiang,Hu Zhongshan,Yang Jingyu,et al.A study on combining multiple classifiers based on evidence theory[J].Chinese Journal of Computer,2001,24(3):231-235.(in Chinese)
[9] Kuncheva L I,Whitaker C J.Measure of diversity in classifier ensembles [J]. Machine Learning,2003,51(2):181-207.
[10] Kuncheva L I,Whitaker C J,Shipp C A,et al.Limits on the majority vote accuracy in classifier fusion [J]. Pattern Analysis Application,2003,6(1):22-31.

备注/Memo

备注/Memo:
基金项目: 江苏省自然科学基金资助项目(BK2002420).
作者简介: 张秀英(1977—),女,博士,lzhxy77@163.com.
更新日期/Last Update: 2007-05-20