RT Journal Article
T1 Automatic Counting and Individual Size and Mass Estimation of Olive-Fruits Through Computer Vision Techniques
A1 Ponce Real, Juan Manuel
A1 Aquino Martín, Arturo
A1 Millán Prior, Borja
A1 Andújar Márquez, José Manuel
AB Fruit grading is an essential post-harvest task in the olive industry, where size-and-mass basedfruit classi cation is especially important when processing high-quality table olives.Within this context, thisresearch presents a new methodology aimed at supporting accurate automatic olive-fruit grading by usingcomputer vision techniques and feature modeling. For its development, a total of 3600 olive-fruits fromnine varieties were photographed, stochastically distributing the individuals on the scene, using an ad-hocdesigned an imaging chamber. Then, an image analysis algorithm, based on mathematical morphology, wasdesigned to individually segment olives and extract descriptive features to estimate their major and minoraxes and their mass. Regarding its accuracy for the individual segmentation of olive-fruits, the algorithmwas proven through 117 captures containing 11 606 fruits, producing only six fruit-segmentation mistakes.Furthermore, by linearly correlating the data obtained by image analysis and the corresponding referencemeasurements, models for estimating the three features were computed. Then, the models were testedon 2700 external validation samples, giving relative errors below 0.80% and 1.05% for the estimation ofthe major and minor axis length for all varieties, respectively. In the case of estimating olive-fruit mass,the models provided relative errors never exceeding 1.16%. The ability of the developed algorithm toindividually segment olives stochastically positioned, along with the lowerror rates of around 1% reported bythe estimation models for the three features, makes the methodology a promising alternative to be integratedinto a newgeneration of improved and non-invasive olive classi cation machines. The newdeveloped systemhas been registered in the Spanish Patent and Trademark Of ce with the number P201930297.
PB Institute of Electrical and Electronics Engineers (IEEE)
SN 2169-3536
YR 2019
FD 2019-05
LK http://hdl.handle.net/10272/16492
UL http://hdl.handle.net/10272/16492
LA eng
NO Ponce Real, J. M., Aquino Martín, A., Millán Prior, B., Andújar Márquez, J. M. (2019). Automatic Counting and Individual Size and Mass Estimation of Olive-Fruits Through Computer Vision Techniques. IEEE Access, 7, 59451–59465. DOI: https://doi.org/10.1109/access.2019.2915169
NO This work and APC were supported in part by the INTERREG Cooperation Program V-A SPAIN-PORTUGAL (POCTEP) 2014-2020, and in part by the ERDF funds under Grant 0155_TECNOLIVO_6_E, within the scope of the TecnOlivo Project.
DS Repositorio Institucional de la Universidad de Huelva
RD 31 may 2026