{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T14:22:07Z","timestamp":1764944527257,"version":"3.46.0"},"reference-count":34,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>The internal quality assessment of potato tubers is a crucial task in agro-laboratory processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in laboratory. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 95% and precision near 97.2% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.<\/jats:p>","DOI":"10.3390\/jimaging11120431","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:02:48Z","timestamp":1764774168000},"page":"431","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid AI Pipeline for Laboratory Detection of Internal Potato Defects Using 2D RGB Imaging"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7829-0410","authenticated-orcid":false,"given":"Slim","family":"Hamdi","sequence":"first","affiliation":[{"name":"CES Laboratory, ENIS National Engineering School, University of Sfax, Sfax B.P. 3038, Tunisia"},{"name":"LIST3N, Universit\u00e9 de Technologie de Troyes, 10300 Troyes, France"},{"name":"Eurocelp SAS, 14 Rue des Pr\u00e9s de Lyon, La Chapelle Saint Luc, 10600 Troyes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7535-1153","authenticated-orcid":false,"given":"Kais","family":"Loukil","sequence":"additional","affiliation":[{"name":"CES Laboratory, ENIS National Engineering School, University of Sfax, Sfax B.P. 3038, Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8919-6420","authenticated-orcid":false,"given":"Adem","family":"Boubaker","sequence":"additional","affiliation":[{"name":"Eurocelp SAS, 14 Rue des Pr\u00e9s de Lyon, La Chapelle Saint Luc, 10600 Troyes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Snoussi","sequence":"additional","affiliation":[{"name":"LIST3N, Universit\u00e9 de Technologie de Troyes, 10300 Troyes, France"},{"name":"EUT+ Data Science Institute, European Union"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Abid","sequence":"additional","affiliation":[{"name":"CES Laboratory, ENIS National Engineering School, University of Sfax, Sfax B.P. 3038, Tunisia"},{"name":"Lab-STICC\/ENSIBS, University of Bretagne du Sud, 56100 Lorient, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"ref_1","unstructured":"Ali, M., Hashim, N., Abd Aziz, S., and Lasekan, O. (2021). Quality Inspection of Food and Agricultural Products Using Artificial Intelligence. Adv. Agric. Food Res. J., 2."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ar\u00e9valo-Royo, J., Flor-Montalvo, F.-J., Latorre-Biel, J.-I., Tino-Ramos, R., Mart\u00ednez-C\u00e1mara, E., and Blanco-Fern\u00e1ndez, J. (2025). AI algorithms in the agrifood industry: Application potential in the Spanish agrifood context. Appl. Sci., 15.","DOI":"10.3390\/app15042096"},{"key":"ref_3","unstructured":"FAO (2023). World Food and Agriculture\u2014Statistical Yearbook 2023, Food and Agriculture Organization of the United Nations."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Imanian, K., Pourdarbani, R., Sabzi, S., Garc\u00eda-Mateos, G., Arribas, J.I., and Molina-Mart\u00ednez, J.M. (2021). Identification of internal defects in potato using spectroscopy and computational intelligence based on majority voting techniques. Foods, 10.","DOI":"10.3390\/foods10050982"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Semyalo, D., Kim, Y., Omia, E., Arief, M.A.A., Kim, H., Sim, E.-Y., Kim, M.S., Baek, I., and Cho, B.-K. (2024). Nondestructive Identification of Internal Potato Defects Using Visible and Short-Wavelength Near-Infrared Spectral Analysis. Agriculture, 14.","DOI":"10.3390\/agriculture14112014"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e14322","DOI":"10.1111\/ppl.14322","article-title":"Growth kinetics, spatialization and quality of potato tubers monitored by magnetic resonance imaging","volume":"176","author":"Musse","year":"2024","journal-title":"Physiol. Plant."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hassan, S.M., Jasinski, M., Leonowicz, Z., Jasinska, E., and Maji, A.K. (2021). Plant Disease Identification Using Shallow Convolutional Neural Network. Agronomy, 11.","DOI":"10.3390\/agronomy11122388"},{"key":"ref_8","first-page":"137","article-title":"Computer vision-based potato defect detection using neural networks and support vector machine","volume":"28","author":"Moallem","year":"2013","journal-title":"Int. J. Robot. Autom."},{"key":"ref_9","unstructured":"Garc\u00eda-Vera, V., Schouten, R.E., Tikunov, Y., Liu, X., Visser, R.G.F., Tan, F., Bovy, A., and Marcelis, L.F.M. (2024). A review of non-destructive techniques for detecting internal defects in agricultural products. Postharvest Biol. Technol., 194."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xu, S., Wang, H., Liang, X., and Lu, H. (2024). Research Progress on Methods for Improving the Stability of Non-Destructive Testing of Agricultural Product Quality. Foods, 13.","DOI":"10.3390\/foods13233917"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"111213","DOI":"10.1016\/j.jfoodeng.2022.111213","article-title":"Automatic detection of multi-type defects on potatoes using multispectral imaging combined with a deep learning model","volume":"336","author":"Yang","year":"2023","journal-title":"J. Food Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2920","DOI":"10.1007\/s12161-019-01654-w","article-title":"Detection and classification of potato defects using multispectral imaging system based on single shot method","volume":"12","author":"Zhang","year":"2019","journal-title":"Food Anal. Methods"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, Z., Lv, P., Sheng, M., Zhang, H., Yang, R., and Shi, T. (2023). Defect detection in food using multispectral and high-definition imaging combined with a newly developed deep learning model. Processes, 11.","DOI":"10.3390\/pr11123295"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"105464","DOI":"10.1016\/j.compag.2020.105464","article-title":"Using a One-Dimensional Convolutional Neural Network with a Conditional Generative Adversarial Network to Classify Plant Electrical Signals","volume":"174","author":"Qin","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","first-page":"301","article-title":"Visualizing internal defects in potatoes using X-ray imaging","volume":"67","author":"Schofield","year":"2005","journal-title":"J. Food Eng."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hajjar, G., Quellec, S., P\u00e9pin, J., Challois, S., and Musse, M. (2021). MRI investigation of internal defects in potato tubers with particular attention to rust spots induced by water stress. Postharvest Biol. Technol., 180.","DOI":"10.1016\/j.postharvbio.2021.111600"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Collewet, G., Moussaoui, S., Quellec, S., Hajjar, G., and Musse, M. (2023). Characterization of potato tuber tissues using spatialized MRI T2 relaxometry. Biomolecules, 13.","DOI":"10.3390\/biom13020286"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2318","DOI":"10.1111\/pce.12548","article-title":"Assessing potato tuber diel growth by means of X-ray computed tomography","volume":"38","author":"Kirchgessner","year":"2015","journal-title":"Plant Cell Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02851513","article-title":"X-ray images of hollow heart potatoes in water","volume":"50","author":"Finney","year":"1973","journal-title":"Am. Potato J."},{"key":"ref_20","first-page":"43","article-title":"Non-destructive Detection of Potato Tubers Internal Defects: Critical Insight on the Use of Time-Resolved Spectroscopy","volume":"34","author":"Ibrahim","year":"2020","journal-title":"Adv. Hortic. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, C., and Xiao, Z. (2021). Potato surface defect detection based on deep transfer learning. Agriculture, 11.","DOI":"10.3390\/agriculture11090863"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Wang, W., Jin, X., Zhang, H., and Sun, H. (2024). DCS-YOLOv5s: A lightweight algorithm for multi-target recognition of seed potatoes based on YOLOv5s. Agronomy, 14.","DOI":"10.3390\/agronomy14112558"},{"key":"ref_23","unstructured":"Alif, M.A.R., and Hussain, M. (2024). YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their applications in agriculture. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, F., Guo, Y., Liu, Y., Lv, H., Zeng, F., and Lv, C. (2025). Improved YOLO v5s-based detection method for external defects in potato. Front. Plant Sci., 16.","DOI":"10.3389\/fpls.2025.1527508"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, X., Fan, J., Yan, F., Hu, H., Zeng, Z., Wu, P., Huang, H., and Zhang, H. (2024). Unsupervised Anomaly Detection via Normal Feature-Enhanced Reverse Teacher\u2013Student Distillation. Electronics, 13.","DOI":"10.3390\/electronics13204125"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109759","DOI":"10.1016\/j.compeleceng.2024.109759","article-title":"Unsupervised Industry Anomaly Detection via Asymmetric Reverse Distillation","volume":"106","author":"Sun","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hamdi, S., Bouindour, S., Snoussi, H., Wang, T., and Abid, M. (2021). End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream. J. Imaging, 7.","DOI":"10.3390\/jimaging7050090"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6169","DOI":"10.1007\/s00371-024-03778-5","article-title":"Unsupervised fur anomaly detection with B-spline noise-guided Multi-directional Feature Aggregation","volume":"41","author":"Wang","year":"2025","journal-title":"Vis. Comput."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"106410","DOI":"10.1016\/j.compag.2021.106410","article-title":"Dual-branch, efficient, channel attention-based crop disease identification","volume":"190","author":"Gao","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Nalan, R., Ram, M.R., Nihal, H.M., Sasirekha, S.P., and Mekala, N. (2025, January 19\u201321). Region-based Crop Yield Prediction using a Transformer-CNN Hybrid Model for Agricultural Forecasting. Proceedings of the 2025 International Conference on Intelligent Computing and Control Systems (ICICCS), Erode, India.","DOI":"10.1109\/ICICCS65191.2025.10985479"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e70576","DOI":"10.1002\/fsn3.70576","article-title":"Enhanced YOLOv11n: A method for potato peel damage detection","volume":"13","author":"Li","year":"2025","journal-title":"Food Sci. Nutr."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, Q., Zhang, Z., Liu, J., and Fang, J. (2025). Detection of Seed Potato Sprouts Based on Improved YOLOv8 Algorithm. Agriculture, 15.","DOI":"10.3390\/agriculture15091015"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhu, R., Wang, H., Wang, X., Huang, J., and Liu, S. (2025). Flaw-YOLOv5s: A lightweight potato surface defect detection algorithm based on multi-scale feature fusion. Agronomy, 15.","DOI":"10.3390\/agronomy15040875"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"26152","DOI":"10.1109\/JSTARS.2025.3614504","article-title":"A Review of Deep-Learning-Based SAR Image Ship Interpretation Technology: The Latest Advances","volume":"18","author":"Chen","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/12\/431\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T14:18:51Z","timestamp":1764944331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/12\/431"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["jimaging11120431"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11120431","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2025,12,3]]}}}