Name
Title | ||
|---|---|---|
Using Feature-Vector Based Analysis, Based on Principal Component Analysis and Independent Component Analysis, for Analyzing Hyperspectral Images |
Abstract | ||
|---|---|---|
Abstract: A pixel in a hyperspectral image can be considered as a mixture of the reflectance spectra of several substances. The mixture coefficients correspond to the (relative) amounts of these substances. The benefit of hyperspectral imagery is that many different substances can be characterised and recognised by their spectral signatures. Independent Component Analysis (ICA) can be used to blindly separate mixed statistically independent signals. Principle Component Analysis (PCA), also, gives interesting results. The next step is to interpret and use the ICA and PCA results efficiently. This can be achieved by using a new technique called Feature-Vector Based Analysis (FVBA), which produces a number of Component-FeatureVector pairs. The obtained Feature Vector and the corresponding Components represent, in this case, the spectral signatures and the corresponding weight coefficients images (the relative concentration maps) of the different constituting sibstances. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/ICIAP.2001.957027 | ICIAP |
Keywords | Field | DocType |
pca result,independent component analysis,analyzing hyperspectral images,spectral signature,principal component analysis,different substance,corresponding components,corresponding weight coefficients image,hyperspectral imagery,different constituting sibstances,hyperspectral image,principle component analysis,pixel,hyperspectral imaging,image analysis,vectors,statistical independence,covariance matrix,remote sensing,hyperspectral sensors,feature vector,spectral signatures | Computer vision,Feature vector,Pattern recognition,Computer science,Hyperspectral imaging,Artificial intelligence,Pixel,Independent component analysis,Covariance matrix,Spectral signature,Principal component analysis,Independence (probability theory) | Conference |
ISBN | Citations | PageRank |
0-7695-1183-X | 0 | 0.34 |
References | Authors | |
1 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hamed Hamid Muhammed | 1 | 15 | 4.48 |
| p ammenberg | 2 | 0 | 0.34 |
| ewert bengtsson | 3 | 135 | 25.36 |