Name
Abstract | ||
|---|---|---|
In this paper, we propose a novel ensemble-based classification system for improving the classification accuracy of hyperspectral images. To generate the ensemble, we run the mean-shift (MS) algorithm several times on different bands randomly selected from the hyperspectral cube and with distinct kernel width parameters. The resulting set of MS maps are then successively labeled via a pair wise labeling procedure with respect to a spectral-based classification map generated by the support vector machine (SVM) classifier. To this end, for each region in the MS maps, the weighted-majority-voting (WMV) rule is applied to the corresponding pixels in the SVM map. The output of this step is a set of spectral-spatial classification maps termed as SVM-MS maps. In order to generate the final classification result, we propose to aggregate this set of SVM-MS maps using the ordered weighted averaging (OWA) operator. The determination of the associated weights is made using the idea of a stress function. The performance of the proposed classification system is assessed on three different hyperspectral datasets acquired by the Reflective Optics System Imaging Spectrometer (ROSIS-03), the Digital Imagery Collection Experiment (HYDICE) and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensors. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/JSTARS.2013.2240437 | Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of |
Keywords | Field | DocType |
geophysical image processing,hyperspectral imaging,image classification,image fusion,support vector machines,aviris sensors,airborne visible/infrared imaging spectrometer,digital imagery collection experiment,hydice,owa fusion operators,rosis-03,reflective optics system imaging spectrometer,svm classifier,svm-ms maps,classification accuracy,ensemble-based classification system,hyperspectral cube,hyperspectral image classification,kernel width parameters,mean-shift algorithm,ordered weighted averaging operator,pair wise labeling procedure,spectral-based classification map,spectral-spatial classification maps,stress function,support vector machine,weighted-majority-voting rule,fusion,hyperspectral images,mean-shift (ms) segmentation,ordered weighted averaging (owa) operator,support vector machine (svm),mean shift algorithm,kernel,vectors,stress | Computer vision,Imaging spectrometer,Pattern recognition,Image fusion,Support vector machine,Hyperspectral imaging,Artificial intelligence,Pixel,Mean-shift,Contextual image classification,Mathematics,Airborne visible/infrared imaging spectrometer | Journal |
Volume | Issue | ISSN |
6 | 2 | 1939-1404 |
Citations | PageRank | References |
7 | 0.51 | 28 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Naif Alajlan | 1 | 839 | 50.51 |
| Yakoub Bazi | 2 | 672 | 43.66 |
| Haikel Al-Hichri | 3 | 31 | 4.09 |
| Farid Melgani | 4 | 1100 | 80.98 |
| Ronald R. Yager | 5 | 9852 | 1562.99 |