A novel approach to hyperspectral band selection based on spectral shape similarity analysis and fast branch and bound search
Authors:
- Shijin LiSLShijin Li
- Jianbin QiuJQJianbin Qiu
- Xinxin YangXYXinxin Yang
- Huan LiuHLHuan Liu
- Dingsheng WanDWDingsheng Wan
- Yuelong ZhuYZYuelong Zhu
Open Access
- 1 January 2014
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 27, 241-250
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61170200, 51079040)
- Key Technology R&D Program of Jiangsu Province (BE2012179)
This publication has 24 references indexed in Scilit:
- In-Sample and Out-of-Sample Model Selection and Error Estimation for Support Vector MachinesIEEE Transactions on Neural Networks and Learning Systems, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- BandClust: An Unsupervised Band Reduction Method for Hyperspectral Remote SensingIEEE Geoscience and Remote Sensing Letters, 2010
- A fast separability-based feature-selection method for high-dimensional remotely sensed image classificationPattern Recognition, 2008
- Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2006
- bigVAT: Visual assessment of cluster tendency for large data setsPattern Recognition, 2005
- Classification of hyperspectral data from urban areas based on extended morphological profilesIEEE Transactions on Geoscience and Remote Sensing, 2005
- Thematic Map ComparisonPhotogrammetric Engineering & Remote Sensing, 2004
- Toward an Optimal Supervised Classifier for the Analysis of Hyperspectral DataIEEE Transactions on Geoscience and Remote Sensing, 2004
- A Cluster Separation MeasureIEEE Transactions on Pattern Analysis and Machine Intelligence, 1979