Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques
Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out m...
| Autores principales: | , , , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | Inglés |
| Publicado: |
2017
|
| Acceso en línea: | http://hdl.handle.net/20.500.11939/5319 |
| _version_ | 1855491905279754240 |
|---|---|
| author | Gómez-Sanchís, Juan Martín-Guerrero, José D. Soria-Olivas, Emilio Martinez-Sober, Marcelino Magdalena-Benedito, Rafael Blasco, José |
| author_browse | Blasco, José Gómez-Sanchís, Juan Magdalena-Benedito, Rafael Martinez-Sober, Marcelino Martín-Guerrero, José D. Soria-Olivas, Emilio |
| author_facet | Gómez-Sanchís, Juan Martín-Guerrero, José D. Soria-Olivas, Emilio Martinez-Sober, Marcelino Magdalena-Benedito, Rafael Blasco, José |
| author_sort | Gómez-Sanchís, Juan |
| collection | ReDivia |
| description | Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach. |
| format | Artículo |
| id | ReDivia5319 |
| institution | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| language | Inglés |
| publishDate | 2017 |
| publishDateRange | 2017 |
| publishDateSort | 2017 |
| record_format | dspace |
| spelling | ReDivia53192025-04-25T14:42:02Z Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques Gómez-Sanchís, Juan Martín-Guerrero, José D. Soria-Olivas, Emilio Martinez-Sober, Marcelino Magdalena-Benedito, Rafael Blasco, José Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach. 2017-06-01T10:12:08Z 2017-06-01T10:12:08Z 2012 JAN 2012 article Gomez-Sanchis, J., Martin-Guerrero, J. D., Soria-Olivas, Emilio, Martinez-Sober, Marcelino, M.-Benedito, Rafael, Blasco, J. (2012). Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques. Expert Systems with Applications, 39(1), 780-785. 0957-4174 http://hdl.handle.net/20.500.11939/5319 10.1016/j.eswa.2011.07.073 en openAccess Impreso |
| spellingShingle | Gómez-Sanchís, Juan Martín-Guerrero, José D. Soria-Olivas, Emilio Martinez-Sober, Marcelino Magdalena-Benedito, Rafael Blasco, José Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title | Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title_full | Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title_fullStr | Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title_full_unstemmed | Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title_short | Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques |
| title_sort | detecting rottenness caused by penicillium genus fungi in citrus fruits using machine learning techniques |
| url | http://hdl.handle.net/20.500.11939/5319 |
| work_keys_str_mv | AT gomezsanchisjuan detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques AT martinguerrerojosed detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques AT soriaolivasemilio detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques AT martinezsobermarcelino detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques AT magdalenabeneditorafael detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques AT blascojose detectingrottennesscausedbypenicilliumgenusfungiincitrusfruitsusingmachinelearningtechniques |