Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques
Loquat (Eriobotrya japonica L.) is an important fruit for the economy of some regions of Spain that is very susceptible to mechanical damage and physiological disorders. These problems depreciate its value and prevent it from being exported. Visible (VIS) and near infrared (NIR) hyperspectral imagin...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Artículo |
| Language: | Inglés |
| Published: |
Elsevier
2021
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11939/6973 https://www.sciencedirect.com/science/article/pii/S0925521420309285 |
| _version_ | 1855492193393836032 |
|---|---|
| author | Munera, Sandra Gómez-Sanchís, Juan Aleixos, Nuria Vila-Francés, Joan Colelli, Giancarlo Cubero, Sergio Soler, Esteban Blasco, José |
| author_browse | Aleixos, Nuria Blasco, José Colelli, Giancarlo Cubero, Sergio Gómez-Sanchís, Juan Munera, Sandra Soler, Esteban Vila-Francés, Joan |
| author_facet | Munera, Sandra Gómez-Sanchís, Juan Aleixos, Nuria Vila-Francés, Joan Colelli, Giancarlo Cubero, Sergio Soler, Esteban Blasco, José |
| author_sort | Munera, Sandra |
| collection | ReDivia |
| description | Loquat (Eriobotrya japonica L.) is an important fruit for the economy of some regions of Spain that is very susceptible to mechanical damage and physiological disorders. These problems depreciate its value and prevent it from being exported. Visible (VIS) and near infrared (NIR) hyperspectral imaging was used to discriminate between external and internal common defects of loquat cv. ‘Algerie’. Two classifiers, random forest (RF) and extreme gradient boost (XGBoost), and different spectral pre-processing techniques were evaluated in terms of their capacity to distinguish between sound and defective features according to three approaches. In the first approach the fruit pixels were classified into two classes, sound or defect, with a 97.5% rate of success; in the second the defective features were considered internal or external defects, achieving a 96.7% rate of success; and in the third approach each type of defect, i.e. purple spot, bruising, scars and flesh browning, were considered separately with a correct classification rate of 95.9%. The results indicated that the XGBoost classifier was the best method in all cases. |
| format | Artículo |
| id | ReDivia6973 |
| institution | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| language | Inglés |
| publishDate | 2021 |
| publishDateRange | 2021 |
| publishDateSort | 2021 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | ReDivia69732025-04-25T14:48:01Z Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques Munera, Sandra Gómez-Sanchís, Juan Aleixos, Nuria Vila-Francés, Joan Colelli, Giancarlo Cubero, Sergio Soler, Esteban Blasco, José Non-destructive Artificial vision H20 Plant diseases N01 Agricultural engineering N20 Agricultural machinery and equipment Eriobotrya japonica Quality Classification Multivariate analysis Loquat (Eriobotrya japonica L.) is an important fruit for the economy of some regions of Spain that is very susceptible to mechanical damage and physiological disorders. These problems depreciate its value and prevent it from being exported. Visible (VIS) and near infrared (NIR) hyperspectral imaging was used to discriminate between external and internal common defects of loquat cv. ‘Algerie’. Two classifiers, random forest (RF) and extreme gradient boost (XGBoost), and different spectral pre-processing techniques were evaluated in terms of their capacity to distinguish between sound and defective features according to three approaches. In the first approach the fruit pixels were classified into two classes, sound or defect, with a 97.5% rate of success; in the second the defective features were considered internal or external defects, achieving a 96.7% rate of success; and in the third approach each type of defect, i.e. purple spot, bruising, scars and flesh browning, were considered separately with a correct classification rate of 95.9%. The results indicated that the XGBoost classifier was the best method in all cases. 2021-01-18T09:33:04Z 2021-01-18T09:33:04Z 2021 article acceptedVersion Munera, S., Gómez-Sanchís, J., Aleixos, N., Vila-Francés, J., Colelli, G., Cubero, S. et al. (2021). Discrimination of common defects in loquat fruit cv.‘Algerie’using hyperspectral imaging and machine learning techniques. Postharvest Biology and Technology, 171, 111356. 0925-5214 http://hdl.handle.net/20.500.11939/6973 10.1016/j.postharvbio.2020.111356 https://www.sciencedirect.com/science/article/pii/S0925521420309285 en Atribución-NoComercial-SinDerivadas 3.0 España http://creativecommons.org/licenses/by-nc-nd/3.0/es/ openAccess Elsevier electronico |
| spellingShingle | Non-destructive Artificial vision H20 Plant diseases N01 Agricultural engineering N20 Agricultural machinery and equipment Eriobotrya japonica Quality Classification Multivariate analysis Munera, Sandra Gómez-Sanchís, Juan Aleixos, Nuria Vila-Francés, Joan Colelli, Giancarlo Cubero, Sergio Soler, Esteban Blasco, José Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title | Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title_full | Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title_fullStr | Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title_full_unstemmed | Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title_short | Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques |
| title_sort | discrimination of common defects in loquat fruit cv algerie using hyperspectral imaging and machine learning techniques |
| topic | Non-destructive Artificial vision H20 Plant diseases N01 Agricultural engineering N20 Agricultural machinery and equipment Eriobotrya japonica Quality Classification Multivariate analysis |
| url | http://hdl.handle.net/20.500.11939/6973 https://www.sciencedirect.com/science/article/pii/S0925521420309285 |
| work_keys_str_mv | AT munerasandra discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT gomezsanchisjuan discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT aleixosnuria discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT vilafrancesjoan discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT colelligiancarlo discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT cuberosergio discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT soleresteban discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques AT blascojose discriminationofcommondefectsinloquatfruitcvalgerieusinghyperspectralimagingandmachinelearningtechniques |