Combining Classifiers in the Problem of Thematic Processing of Hyperspectral Aerospace Images
- Authors: Dmitriev E.V.1, Kozoderov V.V.2, Dementyev A.O.1, Safonova A.N.3
-
Affiliations:
- Institute of Numerical Mathematics
- Moscow State University
- Institute of Space and Information Technologies
- Issue: Vol 54, No 3 (2018)
- Pages: 213-221
- Section: Analysis and Synthesis of Signals and Images
- URL: https://journals.rcsi.science/8756-6990/article/view/212428
- DOI: https://doi.org/10.3103/S8756699018030019
- ID: 212428
Cite item
Abstract
This paper describes a problem of thematic processing of hyperspectral aerospace images. A recommended technique is based on a decoding algorithm and makes it possible to construct an effective algorithm of multiclass classification based on combining standard algorithms of binary classification of various complexity. The reason for choosing the configuration of the classification algorithm is given. Test calculations based on model and real data are used to show the effectiveness of the proposed approach to recognizing objects from hyperspectral images.
About the authors
E. V. Dmitriev
Institute of Numerical Mathematics
Author for correspondence.
Email: yegor@mail.ru
Russian Federation, ul. Gubkina 8, Moscow, 119333
V. V. Kozoderov
Moscow State University
Email: yegor@mail.ru
Russian Federation, Leninskie Gory 1, Moscow, 119991
A. O. Dementyev
Institute of Numerical Mathematics
Email: yegor@mail.ru
Russian Federation, ul. Gubkina 8, Moscow, 119333
A. N. Safonova
Institute of Space and Information Technologies
Email: yegor@mail.ru
Russian Federation, ul. Academika Kirenskogo 26, korp. 1, Krasnoyarsk, 660074
Supplementary files
