Robust classification of texture land forest inventory based on model of minimally sufficient features

Robust classification of texture land forest inventory based on model of minimally sufficient features

Method for automated classification of ground forest inventory images based on the proposed mathematical model developed. The general model is represented by the statistical characteristics of images and fractal dimension of texture. Experimental means were determined minimally sufficient characteri...

Full description

Bibliographic Details
Main Authors: Ipatov Yury, Krevetsky Alexandr, Andrianov Yury, Sokolov Boris
Format: Article
Language:English
Published: Institut za istrazivanja i projektovanja u privredi 2017-01-01
Series:Istrazivanja i projektovanja za privredu
Subjects:
image classification
image model
statistical characteristics
fractal dimension of the scene
neural network without a teacher
Online Access:https://scindeks-clanci.ceon.rs/data/pdf/1451-4117/2017/1451-41171703236I.pdf
id doaj-c383d92fb7f34b509fdd0719359a8f9e
record_format Article
spelling doaj-c383d92fb7f34b509fdd0719359a8f9e2021-04-02T17:13:53ZengInstitut za istrazivanja i projektovanja u privrediIstrazivanja i projektovanja za privredu1451-41171821-31972017-01-011532362411451-41171703236IRobust classification of texture land forest inventory based on model of minimally sufficient featuresIpatov Yury0Krevetsky Alexandr1Andrianov Yury2Sokolov Boris3Volga State University of Technology, Yoshkar-Ola, RussiaVolga State University of Technology, Yoshkar-Ola, RussiaVolga State University of Technology, Yoshkar-Ola, RussiaSaint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences (SPIIRAS), Saint Petersburg, RussiaMethod for automated classification of ground forest inventory images based on the proposed mathematical model developed. The general model is represented by the statistical characteristics of images and fractal dimension of texture. Experimental means were determined minimally sufficient characteristics to solve the problem of robust classification. Neural network based on unsupervised self-organizing maps used as a classifier. Figures obtained discounts of the proposed approach on real digital images.https://scindeks-clanci.ceon.rs/data/pdf/1451-4117/2017/1451-41171703236I.pdfimage classificationimage modelstatistical characteristicsfractal dimension of the sceneneural network without a teacher
collection DOAJ
language English
format Article
sources DOAJ
author Ipatov Yury
Krevetsky Alexandr
Andrianov Yury
Sokolov Boris
spellingShingle Ipatov Yury
Krevetsky Alexandr
Andrianov Yury
Sokolov Boris
Robust classification of texture land forest inventory based on model of minimally sufficient features
Istrazivanja i projektovanja za privredu
image classification
image model
statistical characteristics
fractal dimension of the scene
neural network without a teacher
author_facet Ipatov Yury
Krevetsky Alexandr
Andrianov Yury
Sokolov Boris
author_sort Ipatov Yury
title Robust classification of texture land forest inventory based on model of minimally sufficient features
title_short Robust classification of texture land forest inventory based on model of minimally sufficient features
title_full Robust classification of texture land forest inventory based on model of minimally sufficient features
title_fullStr Robust classification of texture land forest inventory based on model of minimally sufficient features
title_full_unstemmed Robust classification of texture land forest inventory based on model of minimally sufficient features
title_sort robust classification of texture land forest inventory based on model of minimally sufficient features
publisher Institut za istrazivanja i projektovanja u privredi
series Istrazivanja i projektovanja za privredu
issn 1451-4117
1821-3197
publishDate 2017-01-01
description Method for automated classification of ground forest inventory images based on the proposed mathematical model developed. The general model is represented by the statistical characteristics of images and fractal dimension of texture. Experimental means were determined minimally sufficient characteristics to solve the problem of robust classification. Neural network based on unsupervised self-organizing maps used as a classifier. Figures obtained discounts of the proposed approach on real digital images.
topic image classification
image model
statistical characteristics
fractal dimension of the scene
neural network without a teacher
url https://scindeks-clanci.ceon.rs/data/pdf/1451-4117/2017/1451-41171703236I.pdf
work_keys_str_mv AT ipatovyury robustclassificationoftexturelandforestinventorybasedonmodelofminimallysufficientfeatures
AT krevetskyalexandr robustclassificationoftexturelandforestinventorybasedonmodelofminimallysufficientfeatures
AT andrianovyury robustclassificationoftexturelandforestinventorybasedonmodelofminimallysufficientfeatures
AT sokolovboris robustclassificationoftexturelandforestinventorybasedonmodelofminimallysufficientfeatures
_version_ 1721554478251900928

Similar Items