Name
Abstract | ||
|---|---|---|
Feature extraction using weighted training (FEWT) samples is proposed in this letter. Different spectral bands (features) play different roles in identification of land-cover classes. In the FEWT, the relative importance of each feature of a training sample in predicting the class label of that sample is obtained and considered as a weight for that feature. Then, the weighted training samples can be used in each arbitrary feature extraction method. In this letter, we use the weighted training samples in supervised locality preserving projection. The experimental results on three popular hyperspectral images show that FEWT has better performance and more speed than some state-of-the-art supervised feature extraction methods using limited number of available training samples. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/LGRS.2015.2402167 | Geoscience and Remote Sensing Letters, IEEE |
Keywords | Field | DocType |
feature extraction,geophysical image processing,hyperspectral imaging,land cover,learning (artificial intelligence),fewt sample,arbitrary feature extraction method,feature extraction using weighted training,hyperspectral images,landcover class identification,supervised locality preserving projection,classification,spectral band,weighted training samples,accuracy,learning artificial intelligence,support vector machines | Computer vision,Locality,Dimensionality reduction,Pattern recognition,Computer science,Support vector machine,Hyperspectral imaging,Feature extraction,Artificial intelligence,Spectral bands | Journal |
Volume | Issue | ISSN |
12 | 7 | 1545-598X |
Citations | PageRank | References |
11 | 0.56 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Maryam Imani | 1 | 61 | 8.65 |
| Hassan Ghassemian | 2 | 396 | 34.04 |