Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning
Fungal infections are a main concern in fruit packing houses since a single infected fruit can spread the infection, causing severe losses. Hence, early detection is crucial. Fluorescence induced by UV light is commonly used to detect infected fruits, but it can harm the eyes and the skin. Hypers...
| Autores principales: | , , , , , , |
|---|---|
| Formato: | poster |
| Lenguaje: | Inglés |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/20.500.11939/8934 |
| _version_ | 1855492590197014528 |
|---|---|
| author | Castillo-Gironés, Salvador Gómez-Sanchis, Juan López-Chulia, Marina Guirao, Alberto Palou, Lluís Souza, Ricardo-Lima-de Blasco, José |
| author_browse | Blasco, José Castillo-Gironés, Salvador Guirao, Alberto Gómez-Sanchis, Juan López-Chulia, Marina Palou, Lluís Souza, Ricardo-Lima-de |
| author_facet | Castillo-Gironés, Salvador Gómez-Sanchis, Juan López-Chulia, Marina Guirao, Alberto Palou, Lluís Souza, Ricardo-Lima-de Blasco, José |
| author_sort | Castillo-Gironés, Salvador |
| collection | ReDivia |
| description | Fungal infections are a main concern in fruit packing houses since a single infected fruit can
spread the infection, causing severe losses. Hence, early detection is crucial. Fluorescence
induced by UV light is commonly used to detect infected fruits, but it can harm the eyes and
the skin. Hyperspectral imaging and chemometrics have already been used to detect early
infected fruits, but novel deep-learning approaches can improve the detection. In this work, 50 oranges Navelate were inoculated with Penicillium digitatum and another 50 oranges were
inoculated with distilled water as a control. After the inoculation, the fruits were stored at 20
ºC and 90 % relative humidity. Images were taken daily from the inoculation for four days,
using a Vis-NIR pushbroom system (900-1700 nm). A total of 500 images were captured,
corrected using white and dark references, cropped to the size of the fruit and divided into a
train (60% of the images), validation (20% of images) and independent test (20% of images)
datasets. A customised convolutional nerual network (CNN) was designed, composed of 3
convolutional layers (16, 32 and 64 filters and a kernel size of 3), followed by 3 max-pooling
layers (pool size 2) and two final dense layers for classification of 128 and 1 neuron (with
sigmoid activation function) which was trained for 800 epochs with a binary cross-entropy loss
function. It was possible to correctly classify 100% of the control oranges and 80% of the
inoculated ones from the second day, demonstrating that it is possible to detect asymptomatic
infected using this technology. |
| format | poster |
| id | ReDivia8934 |
| institution | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| record_format | dspace |
| spelling | ReDivia89342025-04-25T14:54:29Z Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning Castillo-Gironés, Salvador Gómez-Sanchis, Juan López-Chulia, Marina Guirao, Alberto Palou, Lluís Souza, Ricardo-Lima-de Blasco, José Hyperspectral imaging J Handling, transport, storage and protection of agricultural products Citrus Penicillium digitatum machine learning Fungal infections are a main concern in fruit packing houses since a single infected fruit can spread the infection, causing severe losses. Hence, early detection is crucial. Fluorescence induced by UV light is commonly used to detect infected fruits, but it can harm the eyes and the skin. Hyperspectral imaging and chemometrics have already been used to detect early infected fruits, but novel deep-learning approaches can improve the detection. In this work, 50 oranges Navelate were inoculated with Penicillium digitatum and another 50 oranges were inoculated with distilled water as a control. After the inoculation, the fruits were stored at 20 ºC and 90 % relative humidity. Images were taken daily from the inoculation for four days, using a Vis-NIR pushbroom system (900-1700 nm). A total of 500 images were captured, corrected using white and dark references, cropped to the size of the fruit and divided into a train (60% of the images), validation (20% of images) and independent test (20% of images) datasets. A customised convolutional nerual network (CNN) was designed, composed of 3 convolutional layers (16, 32 and 64 filters and a kernel size of 3), followed by 3 max-pooling layers (pool size 2) and two final dense layers for classification of 128 and 1 neuron (with sigmoid activation function) which was trained for 800 epochs with a binary cross-entropy loss function. It was possible to correctly classify 100% of the control oranges and 80% of the inoculated ones from the second day, demonstrating that it is possible to detect asymptomatic infected using this technology. 2024-06-06T11:54:04Z 2024-06-06T11:54:04Z 2023 poster Castillo-Gironés, S., Gómez-Sanchis, J., Lopez-Chulia, M., Guirao-Carrascosa, A., Palou, L., Lima de Souza, R. F., Blasco, J. (2023). Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning. II International Conference Cost Action 19145 SENSORFINT — European Network for assuring food integrity using non-destructive spectral sensors, Berlín, p. 105. [Poster presentation] https://hdl.handle.net/20.500.11939/8934 en 2023-06-05 SensorFINT conference & AK Chemometrik und Qualitätssicherung Annual Workshop Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ openAccess electronico |
| spellingShingle | Hyperspectral imaging J Handling, transport, storage and protection of agricultural products Citrus Penicillium digitatum machine learning Castillo-Gironés, Salvador Gómez-Sanchis, Juan López-Chulia, Marina Guirao, Alberto Palou, Lluís Souza, Ricardo-Lima-de Blasco, José Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title | Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title_full | Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title_fullStr | Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title_full_unstemmed | Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title_short | Early detection of infection by Penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| title_sort | early detection of infection by penicillium digitatum in oranges using hyperspectral imaging and machine learning |
| topic | Hyperspectral imaging J Handling, transport, storage and protection of agricultural products Citrus Penicillium digitatum machine learning |
| url | https://hdl.handle.net/20.500.11939/8934 |
| work_keys_str_mv | AT castillogironessalvador earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT gomezsanchisjuan earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT lopezchuliamarina earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT guiraoalberto earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT paloulluis earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT souzaricardolimade earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning AT blascojose earlydetectionofinfectionbypenicilliumdigitatuminorangesusinghyperspectralimagingandmachinelearning |