Engineering & Technologies, 2016, 9(7), 1001-1011 ~ ~ ~ УДК 528.85 The Performance of Classifi ers in the Task of Thematic Processing of Hyperspectral Images Egor V. Dmitriev*a,b a and Vladimir V. Kozoderovc Institute of Numerical Mathematics RAS 8 Gubkina Str., Moscow, 119333, Russia bMoscow Institute for Physics and Technology (State University) M.V. Lomonosov Moscow State University Received 19.05.2016, received in revised form 27.07.2016, accepted 26.08.2016 The performance of the spectral classifi cation methods is analyzed for the problem of hyperspectral remote sensing of soil and vegetation. <...> The characteristic features of metric classifi ers, parametric Bayesian classifi ers and multiclass support vector machines are discussed. <...> The results of classifi cation of hyperspectral airborne images by using the specifi ed above methods and comparative analysis are demonstrated. <...> The advantages of the use of nonlinear classifi ers are shown. <...> It is also shown, the similarity of the results of some modifi cations of support vector machines and Bayesian classifi cation. <...> Citation: Dmitriev E.V., Kozoderov V.V. The performance of classifi ers in the task of thematic processing of hyperspectral images, J. Sib. <...> All rights reserved * Corresponding author E-mail address: yegor@mail.ru 9 Institutskiy per., Dolgoprudny, 141700, Russia c 1 Leninskiye Gory, Moscow, 119991, Russia # 1001 # Egor V. Dmitriev and Vladimir V. Kozoderov. <...> The Performance of Classifi ers in the Task of Thematic Processing… Эффективность классификаторов в задаче тематической обработки гиперспектральных изображений Е. <...> Introduction At the present time, remote sensing measurements are widely used in forest inventories. <...> Traditional approaches are based on the concept of vegetation indices calculated with the use of multispectral aerospace images in visible and near infrared region (VNIR). <...> The most part of actually existing sensors are oriented to obtaining multispectral images in 3-5 key VNIR spectral bands. <...> Such methods allows obtaining assessments of the structure and productivity of forest stands for large enough areas [1]. <...> However, it is known that the employment of such kind of measurements provides not enough accurate estimates because of the coarse spectral resolution of multispectral instruments [2, 3]. <...> The hyperspectral remote sensing is <...>