{"title":"基于经验模态分解的高光谱图像分类决策融合","authors":"B. Demir, S. Erturk","doi":"10.1109/SIU.2010.5651526","DOIUrl":null,"url":null,"abstract":"This paper proposes an Empirical Mode Decomposition (EMD) based decision fusion approach to improve hyperspectral image classification accuracy. EMD is a adaptive signal decomposition method that iteratively decomposes the data into Intrinsic Mode Functions (IMFs). In the proposed approach, firstly two dimensional EMD is applied to each hyperspectral image band. Then, the first IMF, the second IMF, the sum of the first and second IMFs and the original data are individually classified using Support Vector Machine (SVM) and the obtained decisions are fused by a decision fusion approach. Experimental results demonstrate that the classification accuracy can be increased using the proposed EMD based decision fusion approach.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Empirical Mode Decomposition based decision fusion for hyperspectral image classification\",\"authors\":\"B. Demir, S. Erturk\",\"doi\":\"10.1109/SIU.2010.5651526\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes an Empirical Mode Decomposition (EMD) based decision fusion approach to improve hyperspectral image classification accuracy. EMD is a adaptive signal decomposition method that iteratively decomposes the data into Intrinsic Mode Functions (IMFs). In the proposed approach, firstly two dimensional EMD is applied to each hyperspectral image band. Then, the first IMF, the second IMF, the sum of the first and second IMFs and the original data are individually classified using Support Vector Machine (SVM) and the obtained decisions are fused by a decision fusion approach. Experimental results demonstrate that the classification accuracy can be increased using the proposed EMD based decision fusion approach.\",\"PeriodicalId\":152297,\"journal\":{\"name\":\"2010 IEEE 18th Signal Processing and Communications Applications Conference\",\"volume\":\"52 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 IEEE 18th Signal Processing and Communications Applications Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SIU.2010.5651526\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE 18th Signal Processing and Communications Applications Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIU.2010.5651526","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Empirical Mode Decomposition based decision fusion for hyperspectral image classification
This paper proposes an Empirical Mode Decomposition (EMD) based decision fusion approach to improve hyperspectral image classification accuracy. EMD is a adaptive signal decomposition method that iteratively decomposes the data into Intrinsic Mode Functions (IMFs). In the proposed approach, firstly two dimensional EMD is applied to each hyperspectral image band. Then, the first IMF, the second IMF, the sum of the first and second IMFs and the original data are individually classified using Support Vector Machine (SVM) and the obtained decisions are fused by a decision fusion approach. Experimental results demonstrate that the classification accuracy can be increased using the proposed EMD based decision fusion approach.