Name
Abstract | ||
|---|---|---|
In this letter, we propose a method aiming at reducing the noise in hyperspectral images based on the nonlinear generalization of principal component analysis (NLPCA). NLPCA is performed by an autoassociative neural network (AANN) that has the hyperspectral image as input and is trained to reconstruct the same image at the output. Due to its topology, characterized by a bottleneck layer, the nonlinear AANN forces the hyperspectral image to be projected in a lower dimensionality feature space by removing noise and both linear and nonlinear correlations between spectral bands. This process permits to obtain enhancements in terms of the quality of the reconstructed hyperspectral image. The results conducted on different hyperspectral images are qualitatively and quantitatively discussed and demonstrate the potentialities of the proposed method, as compared with similar approaches such as PCA and kernel PCA. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/LGRS.2015.2389269 | Geoscience and Remote Sensing Letters, IEEE |
Keywords | Field | DocType |
geophysical image processing,hyperspectral imaging,image denoising,image enhancement,image reconstruction,infrared imaging,learning (artificial intelligence),neural nets,principal component analysis,aann,nlpca,autoassociative neural network,image quality enhancement,kernel pca,linear correlation,noise removal,nonlinear correlation,nonlinear principal component analysis,thermal hyperspectral image reconstruction,visible hyperspectral imaging,image quality,noise reduction,nonlinear principal component analysis (nlpca),thermal hyperspectral images,learning artificial intelligence,signal to noise ratio | Iterative reconstruction,Noise reduction,Computer vision,Feature vector,Full spectral imaging,Pattern recognition,Signal-to-noise ratio,Kernel principal component analysis,Hyperspectral imaging,Artificial intelligence,Mathematics,Principal component analysis | Journal |
Volume | Issue | ISSN |
12 | 6 | 1545-598X |
Citations | PageRank | References |
2 | 0.39 | 11 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Giorgio A. Licciardi | 1 | 40 | 4.82 |
| Jocelyn Chanussot | 2 | 4145 | 272.11 |