A Novel Approach to the Selection of Robust and Invariant Features for Classification of Hyperspectral Images

Author(s):  
Lorenzo Bruzzone ◽  
Claudio Persello
Author(s):  
R. Hänsch ◽  
O. Hellwich

The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limited to a subset of all available data dimensions which is found by band selection techniques or other methods of dimensionality reduction. This work applies Projection-Based Random Forests to hyperspectral images, which not only overcome the need of an explicit feature extraction, but also provide mechanisms to automatically select spectral bands that contain original (i.e. non-redundant) as well as highly meaningful information for the given classification task. The proposed method is applied to four challenging hyperspectral datasets and it is shown that the effective number of spectral bands can be considerably limited without loosing too much of classification performance, e.g. a loss of 1 % accuracy if roughly 13 % of all available bands are used.


Author(s):  
R. Hänsch ◽  
O. Hellwich

The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limited to a subset of all available data dimensions which is found by band selection techniques or other methods of dimensionality reduction. This work applies Projection-Based Random Forests to hyperspectral images, which not only overcome the need of an explicit feature extraction, but also provide mechanisms to automatically select spectral bands that contain original (i.e. non-redundant) as well as highly meaningful information for the given classification task. The proposed method is applied to four challenging hyperspectral datasets and it is shown that the effective number of spectral bands can be considerably limited without loosing too much of classification performance, e.g. a loss of 1 % accuracy if roughly 13 % of all available bands are used.


2019 ◽  
Vol 1 (7) ◽  
pp. 19-23
Author(s):  
S. I. Surkichin ◽  
N. V. Gryazeva ◽  
L. S. Kholupova ◽  
N. V. Bochkova

The article provides an overview of the use of photodynamic therapy for photodamage of the skin. The causes, pathogenesis and clinical manifestations of skin photodamage are considered. The definition, principle of action of photodynamic therapy, including the sources of light used, the classification of photosensitizers and their main characteristics are given. Analyzed studies that show the effectiveness and comparative evaluation in the selection of various light sources and photosensitizing agents for photodynamic therapy in patients with clinical manifestations of photodamage.


Sign in / Sign up

Export Citation Format

Share Document