An adaptative classifier for the recognition of targets in CCD/CBERS images
This work presents an integrated neural classifier aiming to increase the accuracy in the recognition of different features inside CCD/CBERS images. Among these features there are native capons and areas of reforestation of Araucaria angustifolia located in the interior and in the proximities of the...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universidade Federal de Uberlândia
2006-12-01
|
Series: | Revista Brasileira de Cartografia |
Subjects: | |
Online Access: | http://www.rbc.ufrj.br/_pdf_58_2006/58_03_9.pdf |
id |
doaj-78c699393eab460f85ead3fbceec4a1e |
---|---|
record_format |
Article |
spelling |
doaj-78c699393eab460f85ead3fbceec4a1e2020-11-25T03:34:58ZengUniversidade Federal de UberlândiaRevista Brasileira de Cartografia0560-46131808-09362006-12-01583293305An adaptative classifier for the recognition of targets in CCD/CBERS imagesAntonio Roberto FormaggioYosio Edemir ShimabukuroJosé Demísio Simões da SilvaCléber RubertViviane TodtThis work presents an integrated neural classifier aiming to increase the accuracy in the recognition of different features inside CCD/CBERS images. Among these features there are native capons and areas of reforestation of Araucaria angustifolia located in the interior and in the proximities of the Sao Francisco de Paula National Forest. This forest is considered the older conservation unit from Rio Grande do Sul state, Brazil . The considered neural classifiers are said integrated because they are constituted of three models of neural nets grouped in two distinct approaches of integration: a) the two-third approach, and b) the credibility criterion approach. The used neural classifiers were: Multi-layer Perceptron, Learning Vector Quantization, and Radial Basis Function. The developed experiments showed that the integrated neural model using the credibility criterion approach contributes for increasing the accuracy in the identification of features, revealing promising for other applications, such as the monitoring in real time of the terrestrial surface.http://www.rbc.ufrj.br/_pdf_58_2006/58_03_9.pdfArtificial Neural NetsCCD sensorCBERS satelliteAraucariaangustifolia. |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Antonio Roberto Formaggio Yosio Edemir Shimabukuro José Demísio Simões da Silva Cléber Rubert Viviane Todt |
spellingShingle |
Antonio Roberto Formaggio Yosio Edemir Shimabukuro José Demísio Simões da Silva Cléber Rubert Viviane Todt An adaptative classifier for the recognition of targets in CCD/CBERS images Revista Brasileira de Cartografia Artificial Neural Nets CCD sensor CBERS satellite Araucariaangustifolia. |
author_facet |
Antonio Roberto Formaggio Yosio Edemir Shimabukuro José Demísio Simões da Silva Cléber Rubert Viviane Todt |
author_sort |
Antonio Roberto Formaggio |
title |
An adaptative classifier for the recognition of targets in CCD/CBERS images |
title_short |
An adaptative classifier for the recognition of targets in CCD/CBERS images |
title_full |
An adaptative classifier for the recognition of targets in CCD/CBERS images |
title_fullStr |
An adaptative classifier for the recognition of targets in CCD/CBERS images |
title_full_unstemmed |
An adaptative classifier for the recognition of targets in CCD/CBERS images |
title_sort |
adaptative classifier for the recognition of targets in ccd/cbers images |
publisher |
Universidade Federal de Uberlândia |
series |
Revista Brasileira de Cartografia |
issn |
0560-4613 1808-0936 |
publishDate |
2006-12-01 |
description |
This work presents an integrated neural classifier aiming to increase the accuracy in the recognition of different features inside CCD/CBERS images. Among these features there are native capons and areas of reforestation of Araucaria angustifolia located in the interior and in the proximities of the Sao Francisco de Paula National Forest. This forest is considered the older conservation unit from Rio Grande do Sul state, Brazil . The considered neural classifiers are said integrated because they are constituted of three models of neural nets grouped in two distinct approaches of integration: a) the two-third approach, and b) the credibility criterion approach. The used neural classifiers were: Multi-layer Perceptron, Learning Vector Quantization, and Radial Basis Function. The developed experiments showed that the integrated neural model using the credibility criterion approach contributes for increasing the accuracy in the identification of features, revealing promising for other applications, such as the monitoring in real time of the terrestrial surface. |
topic |
Artificial Neural Nets CCD sensor CBERS satellite Araucariaangustifolia. |
url |
http://www.rbc.ufrj.br/_pdf_58_2006/58_03_9.pdf |
work_keys_str_mv |
AT antoniorobertoformaggio anadaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT yosioedemirshimabukuro anadaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT josedemisiosimoesdasilva anadaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT cleberrubert anadaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT vivianetodt anadaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT antoniorobertoformaggio adaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT yosioedemirshimabukuro adaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT josedemisiosimoesdasilva adaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT cleberrubert adaptativeclassifierfortherecognitionoftargetsinccdcbersimages AT vivianetodt adaptativeclassifierfortherecognitionoftargetsinccdcbersimages |
_version_ |
1724556333463633920 |