A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions
We present a method for multispectral seed phenotyping as a fast and robust tool for managing genebank accessions. A multispectral vision system was used to take images of the seeds of 20 diverse varieties of rice (approximately 30 seeds for each variety). This was followed by extraction of feature...
| Autores principales: | , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Cambridge University Press
2016
|
| Acceso en línea: | https://hdl.handle.net/10568/165399 |
| _version_ | 1855532537227509760 |
|---|---|
| author | Hansen, Michael Adsetts Edberg Hay, Fiona R. Carstensen, Jens Michael |
| author_browse | Carstensen, Jens Michael Hansen, Michael Adsetts Edberg Hay, Fiona R. |
| author_facet | Hansen, Michael Adsetts Edberg Hay, Fiona R. Carstensen, Jens Michael |
| author_sort | Hansen, Michael Adsetts Edberg |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | We present a method for multispectral seed phenotyping as a fast and robust tool for managing genebank accessions. A multispectral vision system was used to take images of the seeds of 20 diverse varieties of rice (approximately 30 seeds for each variety). This was followed by extraction of feature information from the images. Multivariate analysis of the feature data was used to classify seed phenotypes according to accession. The proportion of correctly classified rice seeds was 93%. We conclude that the multispectral image analysis could play a role in comparing incoming seeds against existing accessions, identifying different seed types within a sample of seeds and/or in checking whether regenerated seeds match the original seeds. |
| format | Journal Article |
| id | CGSpace165399 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2016 |
| publishDateRange | 2016 |
| publishDateSort | 2016 |
| publisher | Cambridge University Press |
| publisherStr | Cambridge University Press |
| record_format | dspace |
| spelling | CGSpace1653992024-12-19T14:13:06Z A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions Hansen, Michael Adsetts Edberg Hay, Fiona R. Carstensen, Jens Michael We present a method for multispectral seed phenotyping as a fast and robust tool for managing genebank accessions. A multispectral vision system was used to take images of the seeds of 20 diverse varieties of rice (approximately 30 seeds for each variety). This was followed by extraction of feature information from the images. Multivariate analysis of the feature data was used to classify seed phenotypes according to accession. The proportion of correctly classified rice seeds was 93%. We conclude that the multispectral image analysis could play a role in comparing incoming seeds against existing accessions, identifying different seed types within a sample of seeds and/or in checking whether regenerated seeds match the original seeds. 2016-09 2024-12-19T12:55:02Z 2024-12-19T12:55:02Z Journal Article https://hdl.handle.net/10568/165399 en Cambridge University Press Hansen, Michael Adsetts Edberg; Hay, Fiona R. and Carstensen, Jens Michael. 2016. A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions. Plant Genet. Resour., Volume 14 no. 3 p. 238-241 |
| spellingShingle | Hansen, Michael Adsetts Edberg Hay, Fiona R. Carstensen, Jens Michael A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title | A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title_full | A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title_fullStr | A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title_full_unstemmed | A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title_short | A virtual seed file: the use of multispectral image analysis in the management of genebank seed accessions |
| title_sort | virtual seed file the use of multispectral image analysis in the management of genebank seed accessions |
| url | https://hdl.handle.net/10568/165399 |
| work_keys_str_mv | AT hansenmichaeladsettsedberg avirtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions AT hayfionar avirtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions AT carstensenjensmichael avirtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions AT hansenmichaeladsettsedberg virtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions AT hayfionar virtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions AT carstensenjensmichael virtualseedfiletheuseofmultispectralimageanalysisinthemanagementofgenebankseedaccessions |