Name
Abstract | ||
|---|---|---|
In this work, basically, the local covariance matrices are used for the purpose of unsupervised segmentation of the hyperspectral images and the effect on the segmentation accuracy is also observed. The acquisition of the hyperspectral images with label (or groundtruth) information is very expensive and time consuming process. For this reason, realizing segmentation without label information brings important advantage in the analysis of the hyperspectral images. Proposed local covariance matrices represent a combined approach for using both spatial and spectral information together which is very important in hyperspectral image processing area. In the simulations, information divergence band selection method for reducing computational complexity and the positive effects of the proposed approach were proven with the experiments. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/SIU.2012.6204461 | Signal Processing and Communications Applications Conference |
Keywords | Field | DocType |
covariance matrices,image segmentation,hyperspectral image acquisition,hyperspectral image segmentation,local covariance matrices,unsupervised segmentation | Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Hyperspectral imaging,Artificial intelligence,Covariance matrix,Kullback–Leibler divergence,Covariance | Conference |
ISBN | Citations | PageRank |
978-1-4673-0054-4 | 0 | 0.34 |
References | Authors | |
9 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gökhan Bilgin | 1 | 62 | 13.18 |
| Erkan Uslu | 2 | 0 | 0.34 |