Application of supervised models and infrared thermography in the identification of mechanical injuries in guava
Introduction: This article is the result of the research entitled “Application of supervised models and infrared thermography in the identification of mechanical damage in guava,” conducted at the University of Cartagena, Colombia, in 2025.
Problem: In agroindustry, fruit classification is based on visual inspection or limited automated systems, making early detection of mechanical damage difficult and leading to economic losses due to post-harvest deterioration, particularly in climacteric fruits such as guava.
Objective: To evaluate the fitting performance of six supervised learning models on a dataset of thermographic images of healthy guavas and guavas with mechanical damage.
Methodology: An adaptation of the CRISP-DM methodology was applied: F1. Business and data understanding, F2. Data preparation, F3. Modeling, and F4. Evaluation and deployment.
Results: Six models were evaluated using cross-validation on 84 thermographic images of healthy and mechanically damaged guavas. Random Forest achieved accuracy, precision, and recall metrics above 0.82 using original images, whereas SVM exceeded 0.85 when cropped images were used.
Conclusion: The feasibility of integrating infrared thermography and supervised learning techniques into automated agroindustrial systems for fruit damage detection is demonstrated.
Originality: A novel approach is proposed based on the integration of infrared thermography and machine learning techniques for the classification of guava fruits with mechanical damage.
Limitations: Image contour segmentation was required to improve model performance, introducing an additional preprocessing stage.
How to Cite
License
Copyright (c) 2026 Ingeniería Solidaria
This work is licensed under a Creative Commons Attribution 4.0 International License.
Cession of rights and ethical commitment
As the author of the article, I declare that is an original unpublished work exclusively created by me, that it has not been submitted for simultaneous evaluation by another publication and that there is no impediment of any kind for concession of the rights provided for in this contract.
In this sense, I am committed to await the result of the evaluation by the journal Ingeniería Solidaría before considering its submission to another medium; in case the response by that publication is positive, additionally, I am committed to respond for any action involving claims, plagiarism or any other kind of claim that could be made by third parties.
At the same time, as the author or co-author, I declare that I am completely in agreement with the conditions presented in this work and that I cede all patrimonial rights, in other words, regarding reproduction, public communication, distribution, dissemination, transformation, making it available and all forms of exploitation of the work using any medium or procedure, during the term of the legal protection of the work and in every country in the world, to the Universidad Cooperativa de Colombia Press.
[1] K. Hong, J. Xie, L. Zhang, D. Sun, and D. Gong, “Effects of chitosan coating on postharvest life and quality of guava (Psidium guajava L.) fruit during cold storage,” Scientia Horticulturae, vol. 144, pp. 172–178, Sep. 2012, doi: https://doi.org/10.1016/j.scienta.2012.07.002.
[2] J. C. Alonso-Cifuentes, P. J. Ordóñez-Morales, and A. F. Rivera-Triviño, “La demanda de guayaba en Colombia,” Corpoica Ciencia y Tecnología Agropecuaria, vol. 18, no. 1, p. 27, 2017, doi: https://doi.org/10.21930/rcta.vol18_num1_art:557.
[3] J. E. Angulo-López, A. C. Flores-Gallegos, C. Torres-León, K. N. Ramírez-Guzmán, G. A. Martínez, and C. N. Aguilar, “Guava (Psidium guajava L.) fruit and valorization of industrialization by-products,” Processes, vol. 9, no. 6, pp. 1–2, Jun. 2021, doi: https://doi.org/10.3390/pr9061075.
[4] F. Solarte, C. G. Muñoz, S. S. N. Maharachchikumbura, and E. Álvarez, “Diversity of Neopestalotiopsis and Pestalotiopsis spp., causal agents of guava scab in Colombia,” Plant Disease, vol. 102, no. 1, p. 49, Jan. 2018, doi: https://doi.org/10.1094/PDIS-01-17-0068-RE.
[5] 17 B. J. Gonçalves, T. M. de O. Giarola, D. F. Pereira, E. V. de B. Vilas Boas, and J. V. de Resende, “Using infrared thermography to evaluate the injuries of cold-stored guava,” Journal of Food Science and Technology, vol. 53, no. 2, pp. 1063–1064, Feb. 2016, doi: https://doi.org/10.1007/s13197-015-2141-4.
[6] Z. Li and C. Thomas, “Quantitative evaluation of mechanical damage to fresh fruits,” Trends in Food Science & Technology, vol. 35, no. 2, pp. 138–150, Feb. 2014, doi: https://doi.org/10.1016/j.tifs.2013.12.001.
[7] T. M. Berry, T. S. Fadiji, T. Defraeye, and U. L. Opara, “The role of horticultural carton vent hole design on cooling efficiency and compression strength: A multi-parameter approach,” Postharvest Biology and Technology, vol. 124, pp. 62–74, Feb. 2017, doi: https://doi.org/10.1016/j.postharvbio.2016.10.005.
[8] S. B. Navarro, “Fisiología de poscosecha,” pp. 16–24, Aug. 2012. [Online]. Available: https://exa.unne.edu.ar/biologia/fisiologia.vegetal/Fisiologiaposcocsecha.pdf
[9] T. Mulkay Vitón, “Pérdidas poscosecha de frutas,” Proyecto de apoyo al fortalecimiento de cadenas de frutales a nivel local, pp. 1–8, 2021. [Online]. Available: https://www.undp.org/sites/g/files/zskgke326/files/migration/cu/a54797bff5636f11bfed463e3529ddfd4cfb-9c5514eecce26b2eb6c4326a4d98.pdf
[10] Departamento Nacional de Planeación (DNP), “Pérdida y desperdicio de alimentos en Colombia,” pp. 29–37, Apr. 2016. [Online]. Available: https://colaboracion.dnp.gov.co/CDT/Prensa/Publicaciones/P%C3%A9rdida%20y%20desperdicio%20de%20alimentos%20en%20colombia.pdf
[11] Organización de las Naciones Unidas para la Alimentación y la Agricultura (FAO), “Pérdidas y desperdicios de alimentos en América Latina y el Caribe,” pp. 2–6, Jul. 2014. [Online]. Available: https://openknowledge.fao.org/server/api/core/bitstreams/6b37c91c-d542-4403-b24e-36b091ed0236/content
[12] R. Usamentiaga, P. Venegas, J. Guerediaga, L. Vega, J. Molleda, and F. Bulnes, “Infrared thermography for temperature measurement and non-destructive testing,” Sensors, vol. 14, no. 7, pp. 12306–12318, Jul. 2014, doi: https://doi.org/10.3390/s140712305.
[13] S. K. Gurupatham, E. Ilksoy, N. Jacob, K. Van Der Horn, and F. Fahad, “Fruit ripeness estimation for avocado using thermal imaging,” in Proc. ASME Int. Mech. Eng. Congr. Expo. (IMECE), 2018, pp. 1–1, doi: https://doi.org/10.1115/IMECE2018-86290.
[14] B. Yanmaz, “Use of infrared thermography in determining meat quality,” Eurasian Journal of Food Science and Technology, vol. 4, no. 2, pp. 54–55, 2020. [Online]. Available: https://dergipark.org.tr/en/pub/ejfst/article/789134
[15] A. T. Atta, B. Ogunsina, A. Adegbenjo, and O. Awe, “Prediction of tomatoes freshness using infrared thermography,” Journal of Agricultural Engineering and Technology, vol. 27, no. 2, pp. 150–154, 2022. [Online]. Available: https://www.researchgate.net/publication/370751209
[16] B. Guo, B. Li, Y. Huang, F. Hao, B. Xu, and Y. Dong, “Bruise detection and classification of strawberries based on thermal images,” Food and Bioprocess Technology, vol. 15, no. 5, pp. 1134–1139, May 2022, doi: https://doi.org/10.1007/s11947-022-02804-5.
[17] R. Jebita, J. S. Jeyanathan, S. Fathima, V. S., S. S., and S. K., “Segmentation of bruises in fruit thermograms during postharvest stage using K-means clustering technique,” in Proc. Int. Conf. Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), 2024, pp. 1–4, doi: https://doi.org/10.1109/INCOS59338.2024.10527591.
[18] N. Fa, R. A. Saputra, and J. Nangi, “Classification of apple maturity based on color using the K-nearest neighbor (KNN) method,” Telematika, vol. 21, no. 1, pp. 55–58, Jun. 2024, doi: https://doi.org/10.31315/telematika.v21i1.11773.
[19] J. M. Dueñas Quesada, “Aprendizaje supervisado para la detección de amenazas web mediante clasificación basada en árboles de decisión,” p. 5, Jun. 2020. [Online]. Available: https://openaccess.uoc.edu/server/api/core/bitstreams/1db8662c-63a0-4382-946a-41243e7ab73c/content
[20] J. Demšar, “Orange data mining,” 2013. [Online]. Available: https://orangedatamining.com/
[21] M. Saba, D. Valdelamar Martínez, L. K. Torres Gil, G. E. Chanchí Golondrino, and M. A. O. Alarcón, “Application of supervised learning methods and information gain methods in the determination of asbestos–cement roofs’ deterioration state,” Applied Sciences, vol. 14, no. 18, p. 15, Sep. 2024, doi: https://doi.org/10.3390/app14188441.
[22] J. Bokrantz, M. Subramaniyan, and A. Skoogh, “Realising the promises of artificial intelligence in manufacturing by enhancing CRISP-DM,” Production Planning & Control, vol. 35, no. 16, pp. 2234–2254, Dec. 2024, doi: https://doi.org/10.1080/09537287.2023.2234882.
[23] F. Fuentes-Peñailillo, G. Carrasco Silva, R. Pérez Guzmán, I. Burgos, and F. Ewertz, “Automating seedling counts in horticulture using computer vision and AI,” Horticulturae, vol. 9, no. 10, p. 1134, Oct. 2023, doi: https://doi.org/10.3390/horticulturae9101134.
[24] S. Kovalenko, S. Kovalenko, A. Kutsenko, M. Godlevskyi, V. Severin, and A. Kovalenko, “Methodology for creating annotated datasets of biological objects in microscopic images,” in Proc. IEEE KhPI Week on Advanced Technology (KhPIWeek), 2024, pp. 1–6, doi: https://doi.org/10.1109/KhPIWeek61434.2024.10878016.
[25] H. Kaur, H. S. Pannu, and A. K. Malhi, “A systematic review on imbalanced data challenges in machine learning,” ACM Computing Surveys, vol. 52, no. 4, p. 1, Jul. 2020, doi: https://doi.org/10.1145/3343440.
[26] P. Kumar, R. Bhatnagar, K. Gaur, and A. Bhatnagar, “Classification of imbalanced data: Review of methods and applications,” IOP Conference Series: Materials Science and Engineering, vol. 1099, no. 1, pp. 1–4, Mar. 2021, doi: https://doi.org/10.1088/1757-899X/1099/1/012077.
[27] P. Thölke et al., “Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data,” NeuroImage, vol. 277, p. 120253, Aug. 2023, doi: https://doi.org/10.1016/j.neuroimage.2023.120253.
[28] P. Godec et al., “Democratized image analytics by visual programming through integration of deep models and small-scale machine learning,” Nature Communications, vol. 10, no. 1, pp. 1–3, Oct. 2019, doi: https://doi.org/10.1038/s41467-019-12397-x.
[29] D. Shin, H. Choi, D. Kim, J. Park, T. K. Yoo, and K. Koh, “Code-free machine learning approach for EVO-ICL vault prediction: A retrospective two-center study,” Translational Vision Science & Technology, vol. 13, no. 4, pp. 2–4, Apr. 2024, doi: https://doi.org/10.1167/tvst.13.4.4
[30] R. Thakur et al., “A comprehensive analysis of image classification: Understanding techniques and exploring data preprocessing using a non-linear approach,” Adv. Nonlinear Var. Inequalities, vol. 26, no. 2, pp. 110–121, Jun. 2023, doi: https://doi.org/10.52783/anvi.v26.i2.287.
[31] H. Ghasemzadeh, R. E. Hillman, and D. D. Mehta, “Toward generalizable machine learning models in speech, language, and hearing sciences: Estimating sample size and reducing overfitting,” J. Speech Lang. Hear. Res., vol. 67, no. 3, pp. 1–7, Mar. 2024, doi: https://doi.org/10.1044/2023_JSLHR-23-00273.
[32] A. Vabalas, E. Gowen, E. Poliakoff, and A. J. Casson, “Machine learning algorithm validation with a limited sample size,” PLoS One, vol. 14, no. 11, pp. 1–5, Nov. 2019, doi: https://doi.org/10.1371/journal.pone.0224365.
[33] G. M. Foody, “Challenges in the real-world use of classification accuracy metrics: From recall and precision to the Matthews correlation coefficient,” PLoS One, vol. 18, no. 10, pp. 1–9, Oct. 2023, doi: https://doi.org/10.1371/journal.pone.0291908.
[34] J. C. Obi, “A comparative study of several classification metrics and their performances on data,” World J. Adv. Eng. Technol. Sci., vol. 8, no. 1, pp. 309–310, Feb. 2023, doi: https://doi.org/10.30574/wjaets.2023.8.1.0054.
[35] A. Marioriyad and P. Ramazi, “Optimizing accuracy, recall, specificity, and precision using ILP,” Mathematics, vol. 13, no. 7, pp. 6–8, Mar. 2025, doi: https://doi.org/10.3390/math13071059.
[36] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, pp. 2–6, Mar. 2024, doi: https://doi.org/10.1038/s41598-024-56706-x.
[37] A. Nouri, B. M. Merzah, S. Mosayyebpour, R. Mousa, and S. Hesaraki, “Evaluation metrics in learning systems: A survey,” Aug. 2025, doi: https://doi.org/10.20944/preprints202508.1594.v1.
[38] M. F. Amin, “Confusion matrix in binary classification problems: A step-by-step tutorial,” J. Eng. Res., vol. 6, no. 5, pp. 1–2, Dec. 2022, doi: https://doi.org/10.21608/erjeng.2022.274526.
[39] T. Xu, Z. Wei, Z. Li, X. Xu, and X. Rao, “Bruise detection of apples based on passive thermal imaging technology,” J. Food Meas. Charact., vol. 18, no. 11, pp. 9125–9130, Nov. 2024, doi: https://doi.org/10.1007/s11694-024-02864-5.
[40] C. Moreno and A. K. Sotelo, “Predicción del crecimiento del hongo Botrytis spp. en fresa (Fragaria ananassa) por medio de termografía infrarroja,” pp. 37–98. [Online]. Available: https://hdl.handle.net/20.500.14625/33631
