Paper Info
Title
Joint segmentation and classification of hyperspectral image using meanshift and sparse representation classifier
Abstract
A novel spectral-spatial classification method based on mean shift and sparse representation classifier (SRC) for hyperspectral images is proposed in this paper. Firstly, the nonnegative matrix factorization, is used as a preprocessing for mean shift. Then, the mean shift algorithm is adopted to partition an image into amount of blocks and get the segmentation map. Through this way, many size-variable and close regions can be got while the boundary information is remained. Secondly, the classification map is obtained by using the SRC. Finally, the fusion of the segmentation map and the classification map is done by using the majority vote rule. Experimental results on two real hyperspectral images demonstrate the effectiveness and good performance of the proposed method.
Year
DOI
Venue
2013
10.1109/IGARSS.2013.6723194
IGARSS
Keywords
Field
DocType
image representation,image fusion,hyperspectral image classification,size variable,classification map,src,mean shift algorithm,sparse matrices,image segmentation,meanshift,hyperspectral image segmentation,spectral spatial classification method,image classification,geophysical image processing,nonnegative matrix factorization,matrix decomposition,boundary information,sparse representation classification,segmentation map fusion,hyperspectral imaging,sparse representation classifier,majority vote rule
Computer vision,Scale-space segmentation,Image fusion,Pattern recognition,Image texture,Computer science,Segmentation,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Mean-shift,Contextual image classification
Conference
Volume
Issue
ISSN
null
null
2153-6996
ISBN
Citations 
PageRank 
978-1-4799-1114-1
0
0.34
References 
Authors
8
5
Name
Order
Citations
PageRank
Xiangrong Zhang149348.70
Yufang Li210.78
Yaoguo Zheng31027.09
Biao Hou436849.04
Xiaojin Hou500.68