Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero
Food fraud is a serious concern for the food industry and consumers. A common fraud is mixing fruit cultivars with similar appearance but significant differences in quality and sensory characteristics, and, hence, different prices. Detecting these abnormalities by visual inspection is challenging...
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | conferenceObject |
| Lenguaje: | Español |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/20.500.11939/8878 |
| _version_ | 1855032871031406592 |
|---|---|
| author | Castillo-Gironés, Salvador Cubero, Sergio López-Chulia, Marina Munera, Sandra Rodríguez, Alejandro Martínez-Onandi, Nerea Aleixos, Nuria Blasco, José |
| author_browse | Aleixos, Nuria Blasco, José Castillo-Gironés, Salvador Cubero, Sergio López-Chulia, Marina Martínez-Onandi, Nerea Munera, Sandra Rodríguez, Alejandro |
| author_facet | Castillo-Gironés, Salvador Cubero, Sergio López-Chulia, Marina Munera, Sandra Rodríguez, Alejandro Martínez-Onandi, Nerea Aleixos, Nuria Blasco, José |
| author_sort | Castillo-Gironés, Salvador |
| collection | ReDivia |
| description | Food fraud is a serious concern for the food industry and consumers. A common
fraud is mixing fruit cultivars with similar appearance but significant differences in quality and
sensory characteristics, and, hence, different prices. Detecting these abnormalities by visual
inspection is challenging when all fruits appear similarly. It is then required tools capable of
separating the fruits by detecting some internal properties, such as those based on spectral
information.
In this study, two loquat cultivars were used: ‘Algerie’, a traditional sweet cultivar, and
‘Xirlero’, a cultivar with good production but slightly astringent. Both are harvested during the
same period and have similar external features but differ in sensory characteristics and price.
Samples corresponding to 300 ‘Xirlero’ and 259 ‘Algerie’ loquats were selected. Hyperspectral
images were acquired in the range 450 – 1000 nm, and the mean spectra of each loquat were
extracted. The spectra collected were divided into a training set (70%) and an independent test
set (30%). Three models were built to classify the two varieties: Partial Least Squares Discriminant
Analysis, Support Vector Machine, and Extra Trees Classifier. All models achieved accuracy
above 85%, indicating that hyperspectral imaging is a promising technology for distinguishing
between very similar cultivars of fruits. |
| format | conferenceObject |
| id | ReDivia8878 |
| institution | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| language | Español |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| record_format | dspace |
| spelling | ReDivia88782025-04-25T14:50:52Z Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero Castillo-Gironés, Salvador Cubero, Sergio López-Chulia, Marina Munera, Sandra Rodríguez, Alejandro Martínez-Onandi, Nerea Aleixos, Nuria Blasco, José N01 Agricultural engineering Loquats Image analysis Cultivated varieties Identification Food fraud is a serious concern for the food industry and consumers. A common fraud is mixing fruit cultivars with similar appearance but significant differences in quality and sensory characteristics, and, hence, different prices. Detecting these abnormalities by visual inspection is challenging when all fruits appear similarly. It is then required tools capable of separating the fruits by detecting some internal properties, such as those based on spectral information. In this study, two loquat cultivars were used: ‘Algerie’, a traditional sweet cultivar, and ‘Xirlero’, a cultivar with good production but slightly astringent. Both are harvested during the same period and have similar external features but differ in sensory characteristics and price. Samples corresponding to 300 ‘Xirlero’ and 259 ‘Algerie’ loquats were selected. Hyperspectral images were acquired in the range 450 – 1000 nm, and the mean spectra of each loquat were extracted. The spectra collected were divided into a training set (70%) and an independent test set (30%). Three models were built to classify the two varieties: Partial Least Squares Discriminant Analysis, Support Vector Machine, and Extra Trees Classifier. All models achieved accuracy above 85%, indicating that hyperspectral imaging is a promising technology for distinguishing between very similar cultivars of fruits. 2024-05-07T09:13:17Z 2024-05-07T09:13:17Z Sevilla conferenceObject Castillo-Gironés, S., Cubero, S., Lopez-Chulia, M., Munera, S., Rodríguez, A., Martínez-Onandi, N., Gómez-Sanchís, J., Aleixos, N., Blasco, J. (2023) Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero. XII Congreso Ibérico de Agroingeniería, Sevilla, 855-861. https://hdl.handle.net/20.500.11939/8878 es 2023-09-04 XII Congreso Ibérico de Agroingeniería Sevilla Este trabajo ha sido parcialmente financiado a través de los proyectos AEI PID2019- 107347RR-C31, C32 y C33 y fondos FEDER, y GVA CIPROM/2021/014. Salvador Castillo agradece a INIA por la beca FPI-INIA PRE2020-094491, con el apoyo de fondos FSE de la Unión Europea. Los autores agradecen a la Cooperativa Agrícola Ruchey de Callosa d’En Sarrià por suministrar la fruta y por el apoyo técnico. Sandra Munera agradece el contrato postdoctoral Juan de la Cierva-Formación (FJC2021-047786-I) cofinanciado por MICIN AEI/10.13039/501100011033 y la UE NextGenerationEU/PRTR. Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ openAccess electronico |
| spellingShingle | N01 Agricultural engineering Loquats Image analysis Cultivated varieties Identification Castillo-Gironés, Salvador Cubero, Sergio López-Chulia, Marina Munera, Sandra Rodríguez, Alejandro Martínez-Onandi, Nerea Aleixos, Nuria Blasco, José Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title | Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title_full | Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title_fullStr | Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title_full_unstemmed | Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title_short | Uso de imagen hiperespectral para la discriminación en postcosecha de variedades similares de níspero |
| title_sort | uso de imagen hiperespectral para la discriminacion en postcosecha de variedades similares de nispero |
| topic | N01 Agricultural engineering Loquats Image analysis Cultivated varieties Identification |
| url | https://hdl.handle.net/20.500.11939/8878 |
| work_keys_str_mv | AT castillogironessalvador usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT cuberosergio usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT lopezchuliamarina usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT munerasandra usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT rodriguezalejandro usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT martinezonandinerea usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT aleixosnuria usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero AT blascojose usodeimagenhiperespectralparaladiscriminacionenpostcosechadevariedadessimilaresdenispero |