Publication:
Comparison of 2D and 3D convolutional neural networks in hyperspectral image analysis of fruits applied to orange bruise detection

Thumbnail Image
Files
Journal of Food Science - 2023 - Pourdarbani - Comparison of 2D and 3D convolutional neural networks in hyperspectral image.pdf(2.01 MB)
Date
2023-10-25
relationships.isAuthorOfPublication
Profile Picture
Person
Profile Picture
Person
relationships.isSecondaryAuthorOf
relationships.isDirectorOf
Authors
Pourdarbani, Raziyeh ; Sabzi, Sajad ; Zohrabi, Reihaneh ; García Mateos, Ginés ; Fernández Beltrán, Rubén ; Molina Martínez, José Miguel ; Rohban, Mohammad H.
item.page.secondaryauthor
Facultades de la UMU::Facultad de Informática
item.page.director
Publisher
Wiley
publication.page.editor
publication.page.department
Informática y Sistemas
DOI
https://doi.org/10.1111/1750-3841.16801
item.page.type
info:eu-repo/semantics/article
Description
Abstract
Recent advances in hyperspectral imaging (HSI) have demonstrated its ability to detect defects in fruit that may not be visible in RGB images. HSIs can be considered 3D images containing two spatial dimensions and one spectral dimension. Therefore, the first question that arises is how to process this type of information, either using 2D or 3D models. In this study, HSI in the 550–900 nm spectral range was used to detect bruising in oranges. Sixty samples of Thompson oranges were subjected to a mechanical bruising process, and HSIs were taken at different time intervals: before bruising, and 8 and 16 h after bruising. The samples were then classified using two convolutional neural network (CNN) models, a shallow 7-layer network (CNN-7) and a deep 18-layer network (CNN-18). In addition, two different input processing approaches are used: using 2D information from each band, and using the full 3D data from each HSI. The 3D models were the most accurate, with 94% correct classification for 3D-CNN-18, compared to 90% for 3D-CNN-7, and less than 83% for the 2D models. Our study suggests that 3D HSI may be a more effective technique for detecting fruit bruising, allowing the development of a fast, accurate, and nondestructive method for fruit sorting.
publication.page.subject
Bruise detection , Computer vision , Deep learning , Hyperspectral imaging , Visible and near infrared spectroscopy
Citation
Journal of Food Science, 2023, vol. 88, no 12, p. 5149-5163.
URI
http://hdl.handle.net/10201/188030
item.page.embargo
Collections
Artículos
Ir a Estadísticas