|
|
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
06/05/2009 |
Data da última atualização: |
01/12/2010 |
Autoria: |
SANTOS, J. A. dos; LAMPARELLI, R. A. C.; TORRES, R. S. |
Afiliação: |
JEFERSON ALEX DOS SANTOS, IC/UNICAMP; RUBENS AUGUSTO CAMARGO LAMPARELLI, IC/UNICAMP; RICARDO DA SILVA TORRES, IC/UNICAMP. |
Título: |
Using relevance feedback for classifying remote sensing images. |
Ano de publicação: |
2009 |
Fonte/Imprenta: |
In: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 14., 2009, Natal. Anais... São José dos Campos: INPE, 2009. |
Páginas: |
p. 7909-7916. |
Idioma: |
Inglês |
Conteúdo: |
This paper presents an interactive technique for remote sensing image classification. In our proposal, users are able to interact with the classification system, indicating regions which are of interest. Furthermore, a genetic programming approach is used to learn user preferences and combine image region descriptors that encode spectral and texture properties. The approach to classify images can be divided into four main steps: (i) image partition and region feature extraction, (ii) identification of the partitions which are of interest, (iii) image segmentation, and (iv) region vectorization. This work describes the obtained results from the first two main steps: partition/extraction of image features and recognition of partitions of interest. So, in the first step the image are partitioned into tiles. Each tile is considered as an independent image and this process starts by the indication of a query image by the user. This query image is assumed to present the same texture and spectral properties of the RSI regions which are of interest. A similarity search is performed and the most similar tiles are returned to the user. The user then indicates if the returned tiles are relevant or non-relevant. By using this feedback, the classification system learns the user needs and tunes itself in order to improve the results in the next iteration. This process is repeated until the user is satisfied with the result. Experiments demonstrate that the proposed method is effective and suitable for image classification tasks. MenosThis paper presents an interactive technique for remote sensing image classification. In our proposal, users are able to interact with the classification system, indicating regions which are of interest. Furthermore, a genetic programming approach is used to learn user preferences and combine image region descriptors that encode spectral and texture properties. The approach to classify images can be divided into four main steps: (i) image partition and region feature extraction, (ii) identification of the partitions which are of interest, (iii) image segmentation, and (iv) region vectorization. This work describes the obtained results from the first two main steps: partition/extraction of image features and recognition of partitions of interest. So, in the first step the image are partitioned into tiles. Each tile is considered as an independent image and this process starts by the indication of a query image by the user. This query image is assumed to present the same texture and spectral properties of the RSI regions which are of interest. A similarity search is performed and the most similar tiles are returned to the user. The user then indicates if the returned tiles are relevant or non-relevant. By using this feedback, the classification system learns the user needs and tunes itself in order to improve the results in the next iteration. This process is repeated until the user is satisfied with the result. Experiments demonstrate that the proposed method is effective and... Mostrar Tudo |
Palavras-Chave: |
Classificação de imagem; Programação genética; Relevance feedback; Semi-automatic Vectorization Approach; Sistema CBIR. |
Thesagro: |
Sensoriamento Remoto. |
Thesaurus Nal: |
Remote sensing. |
Categoria do assunto: |
-- |
Marc: |
LEADER 02307nga a2200241 a 4500 001 1048872 005 2010-12-01 008 2009 bl uuuu u00u1 u #d 100 1 $aSANTOS, J. A. dos 245 $aUsing relevance feedback for classifying remote sensing images. 260 $c2009 300 $ap. 7909-7916. 520 $aThis paper presents an interactive technique for remote sensing image classification. In our proposal, users are able to interact with the classification system, indicating regions which are of interest. Furthermore, a genetic programming approach is used to learn user preferences and combine image region descriptors that encode spectral and texture properties. The approach to classify images can be divided into four main steps: (i) image partition and region feature extraction, (ii) identification of the partitions which are of interest, (iii) image segmentation, and (iv) region vectorization. This work describes the obtained results from the first two main steps: partition/extraction of image features and recognition of partitions of interest. So, in the first step the image are partitioned into tiles. Each tile is considered as an independent image and this process starts by the indication of a query image by the user. This query image is assumed to present the same texture and spectral properties of the RSI regions which are of interest. A similarity search is performed and the most similar tiles are returned to the user. The user then indicates if the returned tiles are relevant or non-relevant. By using this feedback, the classification system learns the user needs and tunes itself in order to improve the results in the next iteration. This process is repeated until the user is satisfied with the result. Experiments demonstrate that the proposed method is effective and suitable for image classification tasks. 650 $aRemote sensing 650 $aSensoriamento Remoto 653 $aClassificação de imagem 653 $aProgramação genética 653 $aRelevance feedback 653 $aSemi-automatic Vectorization Approach 653 $aSistema CBIR 700 1 $aLAMPARELLI, R. A. C. 700 1 $aTORRES, R. S. 773 $tIn: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 14., 2009, Natal. Anais... São José dos Campos: INPE, 2009.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registros recuperados : 1 | |
1. | ![Imagem marcado/desmarcado](/consulta/web/img/desmarcado.png) | ALBERTON, B.; MARTIN, T. C. M.; ROCHA, H. R. da; RICHARDSON, A. D.; MOURA, M. S. B. de; TORRES, R. S.; MORELLATO, L. P. C. Relationship between tropical leaf phenology and ecosystem productivity using phenocameras. Frontiers in Environmental Science, v. 11, 1223219, Sept. 2023.Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 2 |
Biblioteca(s): Embrapa Semiárido. |
| ![Visualizar detalhes do registro](/consulta/web/img/visualizar.png) ![Acesso ao objeto digital](/consulta/web/img/pdf.png) ![Imprime registro no formato completo](/consulta/web/img/print.png) |
Registros recuperados : 1 | |
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|