RT Journal Article
T1 Olive-Fruit Variety Classification by Means of Image Processing and Convolutional Neural Networks
A1 Ponce Real, Juan Manuel
A1 Aquino Martín, Arturo
A1 Andújar Márquez, José Manuel
AB The automation of classifcation and grading of horticultural products attending to differentfeatures comprises a major challenge in food industry. Thus, focused on the olive sector, which boasts of ahuge range of cultivars, it is proposed a methodology for olive-fruit variety classifcation, approaching it asan image classifcation problem. To that purpose, 2,800 fruits belonging to seven different olive varietieswere photographed. After processing these initial captures by means of image processing techniques,the resulting set of images of individual fruits were used to train, and continuedly to externally validate, theimplementations of six different Convolutional Neural Networks architectures. This, in order to computethe classifers with which perform the variety categorization of the fruits. Remarkable hit rates wereobtained after testing the classifers on the corresponding external validation sets. Thus, it was yieldeda top accuracy of 95.91% when using the Inception-ResnetV2 architecture. The results suggest that theproposed methodology, once integrated into industrial conveyor belts, promises to be an advanced solutionto postharvest olive-fruit processing and classifcation.
PB Institute of Electrical and Electronics Engineers
SN 2169-3536
YR 2019
FD 2019-10
LK http://hdl.handle.net/10272/17618
UL http://hdl.handle.net/10272/17618
LA eng
NO Ponce Real, J. M., Aquino Matín, A.,  Andujar Márquez, J. M. (2019). Olive-Fruit Variety Classification by Means of Image Processing and Convolutional Neural Networks. IEEE Access, 7, 147629–147641. DOI: https://doi.org/10.1109/access.2019.2947160
DS Repositorio Institucional de la Universidad de Huelva
RD 2 jun 2026