UM
Autoencoder with extended morphological profile for hyperspectral image classification
Luo H.3; Tang Y.Y.3; Yang X.3; Yang L.2; Li H.1
2017-07-19
Source Publication2017 3rd IEEE International Conference on Cybernetics, CYBCONF 2017 - Proceedings
AbstractA simple but efficient method is proposed in this paper to exploit the capability of autoencoder with Extended Morphological Profile (EMP) for hyperspectral image (HSI) classification. In our work, the extended morphological profile is employed to extract the spatial information, then we join it with the spectral feature to describe the spectral- spatial property of the hyperspectral image. The obtained features are then fed into an autoencoder as input. After pre-training, the reconstruction layer is removed, then the network is equipped with a logistic regression at the last layer, with the role of supervised fine-tuning and classification. Experiments on KSC data set indicates that the proposed scheme can indeed achieve better performance of feature learning than the primitive features.
DOI10.1109/CYBConf.2017.7985761
URLView the original
Language英語
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionUniversity of Macau
Affiliation1.Huazhong University of Science and Technology
2.Guangxi University
3.Universidade de Macau
Recommended Citation
GB/T 7714
Luo H.,Tang Y.Y.,Yang X.,et al. Autoencoder with extended morphological profile for hyperspectral image classification[C],2017.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo H.]'s Articles
[Tang Y.Y.]'s Articles
[Yang X.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo H.]'s Articles
[Tang Y.Y.]'s Articles
[Yang X.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo H.]'s Articles
[Tang Y.Y.]'s Articles
[Yang X.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.