| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Agricultura Digital. |
|
Data corrente: |
06/03/1998 |
|
Data da última atualização: |
03/08/2007 |
|
Autoria: |
MOREIRA, J.; COSTA, L. da F. |
|
Título: |
Neural-based color image segmentation and classification using self-organizing maps. |
|
Ano de publicação: |
1996 |
|
Fonte/Imprenta: |
In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO GRÁFICA E PROCESSAMENTO DE IMAGENS, 9., 1996, Caxambu. Anais... Caxambu: SBC, 1996. |
|
Páginas: |
p.47-54. |
|
Idioma: |
Inglês |
|
Notas: |
Evento conhecido como: SIBGRAPI. Editado por L. Velho, A. de Albuquerque e R. A. Lotufo. |
|
Conteúdo: |
This paper presents a method for color image segmentation which uses classification to group pixels into regions. The chromaticity is used as data source for the method because it is normalized and considers only hue and saturation, excluding the luminance component. The classification is carried out by means of a Self-Organizing Map (SOM), wich is employed to obtain the main chromaticities present in the image. Then, each pixel is classified according to the identified classes. The number of classes is a priori unknown and the artificial neural network that implements the SOM is used to determine the main classes. The detection of the classes in the SOM is done by using a K-means segmentation. The obtained results substantiate the feasibility of the method, whose performance is compared, for evaluation, to human-assisted segmentation. A comparison of the method with a segmentation based on the k-nearest-neighbor classification is also presented. |
|
Palavras-Chave: |
Computação gráfica; Processamento de imagens. |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 01632naa a2200181 a 4500
001 1006058
005 2007-08-03
008 1996 bl uuuu u00u1 u #d
100 1 $aMOREIRA, J.
245 $aNeural-based color image segmentation and classification using self-organizing maps.
260 $c1996
300 $ap.47-54.
500 $aEvento conhecido como: SIBGRAPI. Editado por L. Velho, A. de Albuquerque e R. A. Lotufo.
520 $aThis paper presents a method for color image segmentation which uses classification to group pixels into regions. The chromaticity is used as data source for the method because it is normalized and considers only hue and saturation, excluding the luminance component. The classification is carried out by means of a Self-Organizing Map (SOM), wich is employed to obtain the main chromaticities present in the image. Then, each pixel is classified according to the identified classes. The number of classes is a priori unknown and the artificial neural network that implements the SOM is used to determine the main classes. The detection of the classes in the SOM is done by using a K-means segmentation. The obtained results substantiate the feasibility of the method, whose performance is compared, for evaluation, to human-assisted segmentation. A comparison of the method with a segmentation based on the k-nearest-neighbor classification is also presented.
653 $aComputação gráfica
653 $aProcessamento de imagens
700 1 $aCOSTA, L. da F.
773 $tIn: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO GRÁFICA E PROCESSAMENTO DE IMAGENS, 9., 1996, Caxambu. Anais... Caxambu: SBC, 1996.
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 : 5 | |
| 5. |  | OLIVEIRA, R. C. de; COSTA, L. da F.; FERNANDES, E. A.; ALVARENGA, B. O. e; MATIOLI, S. R.; BELETTI, M. E. Bone histomorphometry of broilers submitted to different phosphorus sources in growing and finisher rations. Pesquisa Agropecuária Brasileira, Brasília, DF, v. 41, n. 10, p. 1517-1523, out. 2006 Título em português: Histomorfometria óssea de frangos de corte submetidos a diferentes fontes de fósforo nas rações de crescimento e terminação.| Biblioteca(s): Embrapa Unidades Centrais. |
|    |
| Registros recuperados : 5 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
