NON-DESTRUCTIVE BRUISE DETECTION IN TABLE OLIVES USING CAPACITIVE SENSING AND MACHINE LEARNING

Öz

Bruising during harvest and postharvest handling reduces the quality, market value, and storage life of table olives. This study proposes a low-cost, fully contactless method for distinguishing bruised olives from sound fruit using capacitive sensing and machine learning. The sensing unit combines a capacitance-to-digital converter with custom copper parallel-plate electrodes. Olives passed individually between the electrodes while capacitance was continuously recorded, producing a 2,000-sample time series containing 18 passages: nine sound and nine bruised olives. Samples were labelled as background, sound olive, or bruised olive. To address background dominance, a balanced dataset of 538 sliding windows was created, and 13 statistical and signal-based features were extracted. Evaluation followed a leakage-free protocol: complete olive passages were held out, overlapping training windows were purged, and scaling and window-length selection were performed only within training folds. For balanced three-class classification, Random Forest achieved 71.93% accuracy, 71.92% balanced accuracy, and a macro F1-score of 0.720, compared with a 33.3% chance level. Olive detection reached an AUC of 0.830, while bruise classification achieved 81.84% accuracy, 84.70% specificity, and an AUC of 0.849. Passage-level analysis, using one feature vector per fruit, correctly classified 17 of 18 olives (94.4%; 95% CI: 0.727–0.999) and detected all bruised samples, with an AUC of 0.988. A conventional random split produced 91.67% window-level accuracy, demonstrating approximately 20 percentage points of leakage-related inflation. These findings support capacitive sensing as a promising, inexpensive approach for contactless olive screening under practical postharvest operating conditions, although validation across larger samples and multiple cultivars is required.

Anahtar Kelimeler

• Capacitive Sensing
• Table Olives
• Bruise Detection
• Machine Learning
• Non-Destructive Testing
• Data Leakage.

Teşekkür

This study received no financial support or grant of any kind, and no support was provided by any funding agency, institution, or organization in the public, commercial, or not-for-profit sectors.

Kaynakça

1. 1. Zipori, I., Dag, A., Tugendhaft, Y., Birger, R., "Mechanical harvesting of table olives: Harvest efficiency and fruit quality", HortScience, Vol. 49, Issue 1, Pages 55-58, 2014.
2. 2. Riquelme, M.T., Barreiro, P., Ruiz-Altisent, M., Valero, C., "Olive classification according to external damage using image analysis", Journal of Food Engineering, Vol. 87, Issue 3, Pages 371-379, 2008.
3. 3. Salvucci, G., Pallottino, F., De Laurentiis, L., Del Frate, F., "Fast olive quality assessment through RGB images and advanced convolutional neural network modeling", European Food Research and Technology, Vol. 248, Pages 1395-1405, 2022.
4. 4. Sola-Guirado, R.R., Bayano-Tejero, S., Aragon-Rodriguez, F., Peña, A., Blanco-Roldan, G., "Bruising pattern of table olives (Manzanilla and Hojiblanca cultivars) caused by hand-held machine harvesting methods", Biosystems Engineering, Vol. 215, Pages 188-202, 2022.
5. 5. Manganiello, R., Moscovini, L., Ortenzi, L., et al., "Artificial intelligence approaches for real-time table olive cultivars quality assessment", European Food Research and Technology, Vol. 252, Page 67, 2026.
6. 6. Macías-Macías, M., Sánchez-Santamaria, H., García Orellana, C.J., González-Velasco, H.M., Gallardo-Caballero, R., García-Manso, A., "Mask R-CNN for quality control of table olives", Multimedia Tools and Applications, Vol. 82, Issue 14, Pages 21657-21671, 2023.
7. 7. Jiménez-Jiménez, F., Castro-García, S., Blanco-Roldán, G.L., et al., "Non-destructive determination of impact bruising on table olives using Vis-NIR spectroscopy", Biosystems Engineering, Vol. 113, Issue 4, Pages 371-378, 2012.
8. 8. Hou, J., Li, C., Ding, H., et al., "Optical non-destructive detection methods for post-harvest fruit quality assessment: progress and perspectives - a review", Journal of Food Measurement and Characterization, Vol. 20, Pages 3899-3928, 2026.

9. 9. Jackson, P.J., Harker, F.R., "Apple bruise detection by electrical impedance measurement", HortScience, Vol. 35, Issue 1, Pages 104-107, 2000.
10. 10. Justicia, M., Madueño, A., Ruiz-Canales, A., et al., "Low-frequency characterisation of mesocarp electrical conductivity in different varieties of olives", Computers and Electronics in Agriculture, Vol. 142, Pages 338-347, 2017.
11. 11. Krapac, M., Gunjača, J., Sladonja, B., Benčić, Đ., Brkić Bubola, K., "Electrical impedance spectroscopy: A tool for determining the harvesting time of olive fruit", Horticulturae, Vol. 10, Issue 11, Page 1131, 2024.
12. 12. El Khaled, D., Castellano, N.N., Gazquez, J.A., et al., "Cleaner quality control system using bioimpedance methods: A review for fruits and vegetables", Journal of Cleaner Production, Vol. 140, Pages 1749-1762, 2017.
13. 13. Ibba, P., Falco, A., Abera, B.D., et al., "Bio-impedance and circuit parameters: An analysis for tracking fruit ripening", Postharvest Biology and Technology, Vol. 159, Page 110978, 2020.
14. 14. Caravia, L., Collins, C., Tyerman, S.D., "Electrical impedance of Shiraz berries correlates with decreasing cell vitality during ripening", Australian Journal of Grape and Wine Research, Vol. 21, Issue 3, Pages 430-438, 2015.
15. 15. González-Merino, R., Hidalgo-Fernández, R.E., Rodero, J., Sola-Guirado, R.R., Sánchez-López, E., "Postharvest geometric characterization of table olive bruising from 3D digitalization", Agronomy, Vol. 12, Issue 11, Page 2732, 2022.
16. 16. Sola-Guirado, R.R., et al., "Cleaning system, batch sorting and traceability between field-industry in the mechanical harvesting of table olives", Postharvest Biology and Technology, Vol. 199, Page 112278, 2023.
17. 17. Analog Devices, "AD7747 24-bit capacitance-to-digital converter datasheet", https://www.analog.com/media/en/technical-documentation/data-sheets/AD7747.pdf, April 2026.