| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Agricultura Digital. Para informações adicionais entre em contato com cnptia.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Agricultura Digital. |
|
Data corrente: |
06/03/2007 |
|
Data da última atualização: |
17/01/2020 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
CAMARGO NETO, J.; MEYER, G. E.; JONES, D. D. |
|
Afiliação: |
JOAO CAMARGO NETO, CNPTIA; GEORGE E. MEYER, Biological Systems Engineering/University of Nebraska; DAVID D. JONES, Biological Systems Engineering/University of Nebraska. |
|
Título: |
Individual leaf extractions from young canopy image using Gustafson-Kessel clustering and a genetic algorithm. |
|
Ano de publicação: |
2006 |
|
Fonte/Imprenta: |
Computers and Electronics in Agriculture, v. 51, p. 66-85, 2006. |
|
DOI: |
10.1016/j.compag.2005.11.002 |
|
Idioma: |
Inglês |
|
Conteúdo: |
The extraction of individual concealed leaves from images of complex plant canopies is a necessary step for taxonomic feature acquisition, species identification, and mapping using a modern personal computer. A new system for individual leaflet extraction was developed and tested, based on connected components, fuzzy clustering and a genetic optimization algorithm. Color images were taken of young, but sparse green canopies, grown in both greenhouse and field conditions. Some images contained individual leaves as connected components, which were readily apparent after separation of the vegetation from its background. Fragments of all other leaves imbedded in the canopy were obtained using the Gustafson?Kessel (GK) clustering algorithm. Each leaf fragment was labeled and placed in a variable length data structure called a chromosome, which represented selected leaf fragments and its neighbors. A genetic algorithm was then used to systematically reassemble the fragments of non-occluded, individual leaves. System performance was evaluated by comparing the number of individual leaves extracted by the computer per plant or plant canopy connected component for various soil/residue backgrounds and time after emergence. 83.5% of the plants in the second week produced at least one computer-extracted leaf for identification. Ninty-two percent of the plants had at least one computer extracted leaf by the third week. 84.7% had more than three computer extracted leaves for identification in the third week. Images of young field plants in multiple species clusters resulted in a 46% leaf extraction rate, but with at least one leaf per connected canopy component. Soybean and velvetleaf leaflets were the easiest to extract. Once individual leaves are extracted, they can be classified using traditional shape and textural feature methods. Computerized individual leaf extraction could assist plant identification and mapping, needed for weed control and crop management. MenosThe extraction of individual concealed leaves from images of complex plant canopies is a necessary step for taxonomic feature acquisition, species identification, and mapping using a modern personal computer. A new system for individual leaflet extraction was developed and tested, based on connected components, fuzzy clustering and a genetic optimization algorithm. Color images were taken of young, but sparse green canopies, grown in both greenhouse and field conditions. Some images contained individual leaves as connected components, which were readily apparent after separation of the vegetation from its background. Fragments of all other leaves imbedded in the canopy were obtained using the Gustafson?Kessel (GK) clustering algorithm. Each leaf fragment was labeled and placed in a variable length data structure called a chromosome, which represented selected leaf fragments and its neighbors. A genetic algorithm was then used to systematically reassemble the fragments of non-occluded, individual leaves. System performance was evaluated by comparing the number of individual leaves extracted by the computer per plant or plant canopy connected component for various soil/residue backgrounds and time after emergence. 83.5% of the plants in the second week produced at least one computer-extracted leaf for identification. Ninty-two percent of the plants had at least one computer extracted leaf by the third week. 84.7% had more than three computer extracted leaves for identification... Mostrar Tudo |
|
Palavras-Chave: |
Algoritmo genético; Fuzzy clustering; Genetic algorithm; Leaf extraction; Machine vision; Visão computacional. |
|
Thesaurus Nal: |
Computer vision. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
Marc: |
LEADER 02750naa a2200241 a 4500
001 1001350
005 2020-01-17
008 2006 bl uuuu u00u1 u #d
024 7 $a10.1016/j.compag.2005.11.002$2DOI
100 1 $aCAMARGO NETO, J.
245 $aIndividual leaf extractions from young canopy image using Gustafson-Kessel clustering and a genetic algorithm.$h[electronic resource]
260 $c2006
520 $aThe extraction of individual concealed leaves from images of complex plant canopies is a necessary step for taxonomic feature acquisition, species identification, and mapping using a modern personal computer. A new system for individual leaflet extraction was developed and tested, based on connected components, fuzzy clustering and a genetic optimization algorithm. Color images were taken of young, but sparse green canopies, grown in both greenhouse and field conditions. Some images contained individual leaves as connected components, which were readily apparent after separation of the vegetation from its background. Fragments of all other leaves imbedded in the canopy were obtained using the Gustafson?Kessel (GK) clustering algorithm. Each leaf fragment was labeled and placed in a variable length data structure called a chromosome, which represented selected leaf fragments and its neighbors. A genetic algorithm was then used to systematically reassemble the fragments of non-occluded, individual leaves. System performance was evaluated by comparing the number of individual leaves extracted by the computer per plant or plant canopy connected component for various soil/residue backgrounds and time after emergence. 83.5% of the plants in the second week produced at least one computer-extracted leaf for identification. Ninty-two percent of the plants had at least one computer extracted leaf by the third week. 84.7% had more than three computer extracted leaves for identification in the third week. Images of young field plants in multiple species clusters resulted in a 46% leaf extraction rate, but with at least one leaf per connected canopy component. Soybean and velvetleaf leaflets were the easiest to extract. Once individual leaves are extracted, they can be classified using traditional shape and textural feature methods. Computerized individual leaf extraction could assist plant identification and mapping, needed for weed control and crop management.
650 $aComputer vision
653 $aAlgoritmo genético
653 $aFuzzy clustering
653 $aGenetic algorithm
653 $aLeaf extraction
653 $aMachine vision
653 $aVisão computacional
700 1 $aMEYER, G. E.
700 1 $aJONES, D. D.
773 $tComputers and Electronics in Agriculture$gv. 51, p. 66-85, 2006.
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 : 7 | |
| 6. |  | MEYER, G. E.; CAMARGO NETO, J.; JONES, D. D.; HINDMAN, T. W. Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images. Computers and Electronics in Agriculture, New York, v. 42, p. 161-180, 2004.| Biblioteca(s): Embrapa Agricultura Digital. |
|    |
| Registros recuperados : 7 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
