A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples
In this paper, a novel weighted multiple-feature classifier based on sparse representation and locally dictionary collaborative representation (WMSLC) is put forward to improve the limited training samples’ hyperspectral image classification performance. The WMSLC method mainly includes the followin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2018-01-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/22797254.2018.1529543 |
| _version_ | 1819168445739040768 |
|---|---|
| author | Jinghui Yang Jinxi Qian |
| author_facet | Jinghui Yang Jinxi Qian |
| author_sort | Jinghui Yang |
| collection | DOAJ |
| description | In this paper, a novel weighted multiple-feature classifier based on sparse representation and locally dictionary collaborative representation (WMSLC) is put forward to improve the limited training samples’ hyperspectral image classification performance. The WMSLC method mainly includes the following steps. Firstly, Spectral feature, Extended Multi-attribute Profile (EMAP) feature and Gabor feature are applied as the multiple feature to describe the hyperspectral image from spectral and different spatial aspects. And weights are utilized to adjust the multiple-feature’s proportions to improve the efficiency of the classification. Secondly, a trade-off is given between different regularization residuals, sparse representation residuals and locally dictionary collaborative representation residuals. Here, the locally adaptive dictionary is implemented to reduce the irrelevant atoms to improve the classification performance. Finally, the test sample is assigned to the class, which has the minimal residuals. Experimental results on two real hyperspectral data sets (Indian Pines and Pavia University) demonstrate that the proposed WMSLC method outperforms several corresponding well-known classifiers when very limited numbers of training samples are available. |
| first_indexed | 2024-12-22T19:03:43Z |
| format | Article |
| id | doaj.art-ff86975f68a0452a832467f8b474b50f |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-12-22T19:03:43Z |
| publishDate | 2018-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-ff86975f68a0452a832467f8b474b50f2022-12-21T18:15:52ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542018-01-015111006102110.1080/22797254.2018.15295431529543A weighted multiple-feature fusion classifier for hyperspectral images with limited training samplesJinghui Yang0Jinxi Qian1China University of GeosciencesChina Academy of Space TechnologyIn this paper, a novel weighted multiple-feature classifier based on sparse representation and locally dictionary collaborative representation (WMSLC) is put forward to improve the limited training samples’ hyperspectral image classification performance. The WMSLC method mainly includes the following steps. Firstly, Spectral feature, Extended Multi-attribute Profile (EMAP) feature and Gabor feature are applied as the multiple feature to describe the hyperspectral image from spectral and different spatial aspects. And weights are utilized to adjust the multiple-feature’s proportions to improve the efficiency of the classification. Secondly, a trade-off is given between different regularization residuals, sparse representation residuals and locally dictionary collaborative representation residuals. Here, the locally adaptive dictionary is implemented to reduce the irrelevant atoms to improve the classification performance. Finally, the test sample is assigned to the class, which has the minimal residuals. Experimental results on two real hyperspectral data sets (Indian Pines and Pavia University) demonstrate that the proposed WMSLC method outperforms several corresponding well-known classifiers when very limited numbers of training samples are available.http://dx.doi.org/10.1080/22797254.2018.1529543Hyperspectralclassificationweighted multiple-featurelimited training samplessparse representationlocally dictionary collaborative representation |
| spellingShingle | Jinghui Yang Jinxi Qian A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples European Journal of Remote Sensing Hyperspectral classification weighted multiple-feature limited training samples sparse representation locally dictionary collaborative representation |
| title | A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples |
| title_full | A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples |
| title_fullStr | A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples |
| title_full_unstemmed | A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples |
| title_short | A weighted multiple-feature fusion classifier for hyperspectral images with limited training samples |
| title_sort | weighted multiple feature fusion classifier for hyperspectral images with limited training samples |
| topic | Hyperspectral classification weighted multiple-feature limited training samples sparse representation locally dictionary collaborative representation |
| url | http://dx.doi.org/10.1080/22797254.2018.1529543 |
| work_keys_str_mv | AT jinghuiyang aweightedmultiplefeaturefusionclassifierforhyperspectralimageswithlimitedtrainingsamples AT jinxiqian aweightedmultiplefeaturefusionclassifierforhyperspectralimageswithlimitedtrainingsamples AT jinghuiyang weightedmultiplefeaturefusionclassifierforhyperspectralimageswithlimitedtrainingsamples AT jinxiqian weightedmultiplefeaturefusionclassifierforhyperspectralimageswithlimitedtrainingsamples |