Neural network technologies for image classification; Proceedings of SPIE; Vol. 9680 : Atmospheric and Ocean Optics: Atmospheric Physics

Detalhes bibliográficos
Parent link:Proceedings of SPIE
Vol. 9680 : Atmospheric and Ocean Optics: Atmospheric Physics.— 2015.— [968023, 4 p.]
Autor principal: Korikov A. M. Anatoly Mikhailovich
Autor Corporativo: Томский политехнический университет Институт кибернетики, ИК
Outros Autores: Tungusova A. V. Anna Vladimirovna
Resumo:Title screen
We analyze the classes of problems with an objective necessity to use neural network technologies, i.e. representation and resolution problems in the neural network logical basis. Among these problems, image recognition takes an important place, in particular the classification of multi-dimensional data based on information about textural characteristics. These problems occur in aerospace and seismic monitoring, materials science, medicine and other. We reviewed different approaches for the texture description: statistical, structural, and spectral. We developed a neural network technology for resolving a practical problem of cloud image classification for satellite snapshots from the spectroradiometer MODIS. The cloud texture is described by the statistical characteristics of the GLCM (Gray Level Co- Occurrence Matrix) method. From the range of neural network models that might be applied for image classification, we chose the probabilistic neural network model (PNN) and developed an implementation which performs the classification of the main types and subtypes of clouds. Also, we chose experimentally the optimal architecture and parameters for the PNN model which is used for image classification. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Режим доступа: по договору с организацией-держателем ресурса
Idioma:inglês
Publicado em: 2015
Assuntos:
Acesso em linha:http://dx.doi.org/10.1117/12.2205896
Formato: Recurso Eletrônico Capítulo de Livro
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=646764

MARC

LEADER 00000nla2a2200000 4500
001 646764
005 20260714161210.0
035 |a (RuTPU)RU\TPU\network\11900 
090 |a 646764 
100 |a 20160315a2015 k y0rusy50 ba 
101 0 |a eng 
105 |a a z 101zy 
135 |a drcn ---uucaa 
181 0 |a i  
182 0 |a b 
200 1 |a Neural network technologies for image classification  |f A. M. Korikov, A. V. Tungusova 
203 |a Text  |c electronic 
300 |a Title screen 
320 |a [References: 7 tit.] 
330 |a We analyze the classes of problems with an objective necessity to use neural network technologies, i.e. representation and resolution problems in the neural network logical basis. Among these problems, image recognition takes an important place, in particular the classification of multi-dimensional data based on information about textural characteristics. These problems occur in aerospace and seismic monitoring, materials science, medicine and other. We reviewed different approaches for the texture description: statistical, structural, and spectral. We developed a neural network technology for resolving a practical problem of cloud image classification for satellite snapshots from the spectroradiometer MODIS. The cloud texture is described by the statistical characteristics of the GLCM (Gray Level Co- Occurrence Matrix) method. From the range of neural network models that might be applied for image classification, we chose the probabilistic neural network model (PNN) and developed an implementation which performs the classification of the main types and subtypes of clouds. Also, we chose experimentally the optimal architecture and parameters for the PNN model which is used for image classification. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only. 
333 |a Режим доступа: по договору с организацией-держателем ресурса 
461 1 |0 (RuTPU)RU\TPU\network\12028  |t Proceedings of SPIE 
463 0 |0 (RuTPU)RU\TPU\network\12443  |t Vol. 9680 : Atmospheric and Ocean Optics: Atmospheric Physics  |o 21st International Symposium, 22–26 June 2015, Tomsk, Russian Federation  |o [proceedings]  |f Institute of Atmospheric Optics SB RAS ; ed. G. G. Matvienko, O. A. Romanovskii  |v [968023, 4 p.]  |d 2015 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
700 1 |a Korikov  |b A. M.  |c radiophysicist, specialist in the field of informatics and computer technology  |c Professor of Tomsk Polytechnic University, doctor of technical sciences  |f 1942-  |g Anatoly Mikhailovich  |3 (RuTPU)RU\TPU\pers\35166 
701 1 |a Tungusova  |b A. V.  |g Anna Vladimirovna 
712 0 2 |a Томский политехнический университет  |b Институт кибернетики, ИК  |c 2010-2017  |9 27025 
801 2 |a RU  |b 63413507  |c 20160404  |g RCR 
856 4 |u http://dx.doi.org/10.1117/12.2205896 
942 |c CF