| |
|
|
 | 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
|
|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Gado de Leite. Para informações adicionais entre em contato com cnpgl.biblioteca@embrapa.br. |
Registro Completo
|
Biblioteca(s): |
Embrapa Gado de Leite; Embrapa Pecuária Sudeste. |
|
Data corrente: |
17/12/2013 |
|
Data da última atualização: |
15/06/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
B - 2 |
|
Autoria: |
McCLURE, M. C.; SONSTEGARD, T. S.; WIGGANS, G. R.; EENENNAAM, A. L. V.; WEBER, K. L.; PENEDO, C. T.; BERRY, D. P.; FLYNN, J.; GARCIA, J. F.; CARMO, A. S.; REGITANO, L. C. de A.; ALBUQUERQUE, M.; SILVA, M. V. G. B.; MACHADO, M. A.; COFFEY, M.; MOORE, K.; BOSCHER, M. Y.; GENESTOUT, L.; MAZZA, R.; TAYLOR, J. F.; SCHNABEL, R. D.; SIMPSON, B.; MARQUES, E.; McEWAN, J. C.; CROMIE, A.; COUTINHO, L. L.; KUEHN, L. A.; KEELE, J. W.; PIPER, E. K.; COOK, J.; WILLIAMS, R.; TASSELL, C. P. V. |
|
Afiliação: |
MATTHEW C. McCLURE, USDA; TAD S. SONSTEGARD, USDA; GEORGE R. WIGGANS, USDA; ALISON L. VAN EENENNAAM, University of California - Davis; KRISTINA L. WEBER, University of California-Davis; CECILIA T. PENEDO, University of California-Davis; DONAGH P. BERRY, Animal and Grassland Research and Innovation Centre, Ireland; JOHN FLYNN, Weatherbys DNA Laboratory, Ireland; JOSÉ F. GARCIA, UNESP; ADRIANA S. CARMO, Deoxi Biotecnologia, Araçatuba; LUCIANA CORREIA DE ALMEIDA REGITANO, CPPSE; MILLA ALBUQUERQUE, USP; MARCOS VINICIUS GUALBERTO B SILVA, CNPGL; MARCO ANTONIO MACHADO, CNPGL; MIKE COFFEY, SRUC, Scotland; KIRSTY MOORE, SRUC, Scotland; MARIE-YVONNE BOSCHER, LABOGENA, France; LUCIE GENESTOUT, LABOGENA, France; RAFFAELE MAZZA, Italian Breeders Association, Roma; JEREMY F. TAYLOR, University of Missouri-Columbia; ROBERT D. SCHNABEL, University of Missouri-Columbia; BARRY SIMPSON, GeneSeek, Neogen Company, Lincoln, USA; ELISA MARQUES, GeneSeek, Neogen Company, Lincoln, USA; JOHN C. McEWAN, AgResearch, Invermay Agricultural Centre, New Zealand; ANDREW CROMIE, Irish Cattle Breeding Federation, Ireland; LUIZ L. COUTINHO, ESALQ/USP; LARRY A. KUEHN, USDA-ARS; JOHN W. KEELE, USDA-ARS; EMILY K. PIPER, University of Queensland, Australia; JIM COOK, University of New England, Australia; ROBERT WILLIAMS, American-International Charolais Association, USA; CURTIS P. VAN TASSELL, USDA. |
|
Título: |
Imputation of microsatellite alleles from dense SNP genotypes for parentage verification across multiple Bos taurus and Bos indicus breeds. |
|
Ano de publicação: |
2013 |
|
Fonte/Imprenta: |
Frontiers in Genetics, v. 4, n. 176, 2013. |
|
Páginas: |
11 p. |
|
Idioma: |
Inglês |
|
Conteúdo: |
To assist cattle producers transition from microsatellite (MS) to single nucleotide polymorphism (SNP) genotyping for parental verification we previously devised an effective and inexpensive method to impute MS alleles from SNP haplotypes. While the reported method was verified with only a limited data set (N = 479) from Brown Swiss, Guernsey, Holstein, and Jersey cattle, some of the MS-SNP haplotype associations were concordant across these phylogenetically diverse breeds. This implied that some haplotypes predate modern breed formation and remain in strong linkage disequilibrium. To expand the utility of MS allele imputation across breeds, MS and SNP data from more than 8000 animals representing 39 breeds (Bos taurus and B. indicus) were used to predict 9410 SNP haplotypes, incorporating an average of 73 SNPs per haplotype, for which alleles from 12 MS markers could be accurately be imputed. Approximately 25% of the MS-SNP haplotypes were present in multiple breeds (N = 2 to 36 breeds). These shared haplotypes allowed for MS imputation in breeds that were not represented in the reference population with only a small increase in Mendelian inheritance inconsistancies. Our reported reference haplotypes can be used for any cattle breed and the reported methods can be applied to any species to aid the transition from MS to SNP genetic markers. While ~91% of the animals with imputed alleles for 12 MS markers had ≤1 Mendelian inheritance conflicts with their parents' reported MS genotypes, this figure was 96% for our reference animals, indicating potential errors in the reported MS genotypes. The workflow we suggest autocorrects for genotyping errors and rare haplotypes, by MS genotyping animals whose imputed MS alleles fail parentage verification, and then incorporating those animals into the reference dataset. MenosTo assist cattle producers transition from microsatellite (MS) to single nucleotide polymorphism (SNP) genotyping for parental verification we previously devised an effective and inexpensive method to impute MS alleles from SNP haplotypes. While the reported method was verified with only a limited data set (N = 479) from Brown Swiss, Guernsey, Holstein, and Jersey cattle, some of the MS-SNP haplotype associations were concordant across these phylogenetically diverse breeds. This implied that some haplotypes predate modern breed formation and remain in strong linkage disequilibrium. To expand the utility of MS allele imputation across breeds, MS and SNP data from more than 8000 animals representing 39 breeds (Bos taurus and B. indicus) were used to predict 9410 SNP haplotypes, incorporating an average of 73 SNPs per haplotype, for which alleles from 12 MS markers could be accurately be imputed. Approximately 25% of the MS-SNP haplotypes were present in multiple breeds (N = 2 to 36 breeds). These shared haplotypes allowed for MS imputation in breeds that were not represented in the reference population with only a small increase in Mendelian inheritance inconsistancies. Our reported reference haplotypes can be used for any cattle breed and the reported methods can be applied to any species to aid the transition from MS to SNP genetic markers. While ~91% of the animals with imputed alleles for 12 MS markers had ≤1 Mendelian inheritance conflicts with their parents' reported MS ... Mostrar Tudo |
|
Palavras-Chave: |
Imputation; Microsatellite; Parentage verification; SNP; STR. |
|
Categoria do assunto: |
G Melhoramento Genético |
|
Marc: |
LEADER 03360naa a2200565 a 4500
001 2154448
005 2023-06-15
008 2013 bl uuuu u00u1 u #d
100 1 $aMcCLURE, M. C.
245 $aImputation of microsatellite alleles from dense SNP genotypes for parentage verification across multiple Bos taurus and Bos indicus breeds.$h[electronic resource]
260 $c2013
300 $a11 p.
520 $aTo assist cattle producers transition from microsatellite (MS) to single nucleotide polymorphism (SNP) genotyping for parental verification we previously devised an effective and inexpensive method to impute MS alleles from SNP haplotypes. While the reported method was verified with only a limited data set (N = 479) from Brown Swiss, Guernsey, Holstein, and Jersey cattle, some of the MS-SNP haplotype associations were concordant across these phylogenetically diverse breeds. This implied that some haplotypes predate modern breed formation and remain in strong linkage disequilibrium. To expand the utility of MS allele imputation across breeds, MS and SNP data from more than 8000 animals representing 39 breeds (Bos taurus and B. indicus) were used to predict 9410 SNP haplotypes, incorporating an average of 73 SNPs per haplotype, for which alleles from 12 MS markers could be accurately be imputed. Approximately 25% of the MS-SNP haplotypes were present in multiple breeds (N = 2 to 36 breeds). These shared haplotypes allowed for MS imputation in breeds that were not represented in the reference population with only a small increase in Mendelian inheritance inconsistancies. Our reported reference haplotypes can be used for any cattle breed and the reported methods can be applied to any species to aid the transition from MS to SNP genetic markers. While ~91% of the animals with imputed alleles for 12 MS markers had ≤1 Mendelian inheritance conflicts with their parents' reported MS genotypes, this figure was 96% for our reference animals, indicating potential errors in the reported MS genotypes. The workflow we suggest autocorrects for genotyping errors and rare haplotypes, by MS genotyping animals whose imputed MS alleles fail parentage verification, and then incorporating those animals into the reference dataset.
653 $aImputation
653 $aMicrosatellite
653 $aParentage verification
653 $aSNP
653 $aSTR
700 1 $aSONSTEGARD, T. S.
700 1 $aWIGGANS, G. R.
700 1 $aEENENNAAM, A. L. V.
700 1 $aWEBER, K. L.
700 1 $aPENEDO, C. T.
700 1 $aBERRY, D. P.
700 1 $aFLYNN, J.
700 1 $aGARCIA, J. F.
700 1 $aCARMO, A. S.
700 1 $aREGITANO, L. C. de A.
700 1 $aALBUQUERQUE, M.
700 1 $aSILVA, M. V. G. B.
700 1 $aMACHADO, M. A.
700 1 $aCOFFEY, M.
700 1 $aMOORE, K.
700 1 $aBOSCHER, M. Y.
700 1 $aGENESTOUT, L.
700 1 $aMAZZA, R.
700 1 $aTAYLOR, J. F.
700 1 $aSCHNABEL, R. D.
700 1 $aSIMPSON, B.
700 1 $aMARQUES, E.
700 1 $aMcEWAN, J. C.
700 1 $aCROMIE, A.
700 1 $aCOUTINHO, L. L.
700 1 $aKUEHN, L. A.
700 1 $aKEELE, J. W.
700 1 $aPIPER, E. K.
700 1 $aCOOK, J.
700 1 $aWILLIAMS, R.
700 1 $aTASSELL, C. P. V.
773 $tFrontiers in Genetics$gv. 4, n. 176, 2013.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Pecuária Sudeste (CPPSE) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
