{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T06:04:11Z","timestamp":1793426651003,"version":"4.5.0"},"reference-count":31,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Innovation Partnership","award":["IRP31"],"award-info":[{"award-number":["IRP31"]}]},{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"crossref","award":["P2-0157"],"award-info":[{"award-number":["P2-0157"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>Potato sorting in post-harvest processing relies heavily on manual visual inspection, which is physically demanding, subjective, and insufficiently scalable for modern packing lines. This study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection. A controlled imaging platform was constructed using commodity hardware, and a dataset of 19,805 manually annotated instances across 1361 images was collected from two geographically distinct farm locations in Slovenia. A systematic benchmark of 25 model configurations spanning five YOLO architecture families\u2014YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLO26\u2014was conducted across three practical quality classes (Edible, Feed, Rotten) using a strict cross-location evaluation protocol in which models were trained on one location and tested on a completely unseen second location. All models achieved strong in-distribution performance (F1 \u2265 0.906), but showed considerable variation under cross-location conditions, with external F1 ranging from 0.792 to 0.918. The yolo26_l configuration achieved the best cross-location performance (F1 = 0.918, mAP@0.5:0.95 = 0.816, \u0394F1 = 0.029), demonstrating that transferable representations are achievable under a standard supervised training protocol. Per-class analysis identified feed detection as the primary generalization bottleneck. The results confirm that affordable RGB-based sorting systems are technically feasible and highlight cross-location evaluation as an essential protocol for assessing real-world deployment readiness.<\/jats:p>","DOI":"10.3390\/foods15122121","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:49:51Z","timestamp":1781257791000},"page":"2121","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OPTIFARM: Benchmarking YOLO Architectures for Location-Robust Potato Quality Detection"],"prefix":"10.3390","volume":"15","author":[{"given":"Tadej","family":"Per\u0161ak","sequence":"first","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Maribor, Smetanova 17, SI-2000 Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7145-6069","authenticated-orcid":false,"given":"Marko","family":"Simoni\u010d","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Maribor, Smetanova 17, SI-2000 Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1518-803X","authenticated-orcid":false,"given":"Jernej","family":"Hernavs","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Maribor, Smetanova 17, SI-2000 Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-0655","authenticated-orcid":false,"given":"Mirko","family":"Ficko","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Maribor, Smetanova 17, SI-2000 Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5922-3792","authenticated-orcid":false,"given":"Simon","family":"Klan\u010dnik","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Maribor, Smetanova 17, SI-2000 Maribor, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s11540-014-9265-1","article-title":"Potatoes for Sustainable Global Food Security","volume":"57","author":"Devaux","year":"2014","journal-title":"Potato Res."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Dahal, K., Li, X.-Q., Tai, H., Creelman, A., and Bizimungu, B. (2019). Improving Potato Stress Tolerance and Tuber Yield Under a Climate Change Scenario\u2014A Current Overview. Front. Plant Sci., 10.","DOI":"10.3389\/fpls.2019.00563"},{"key":"ref_3","unstructured":"(2026, April 19). Statistical Office of the Republic of Slovenia. Available online: https:\/\/www.stat.si\/StatWeb\/."},{"key":"ref_4","unstructured":"Kitinoja, L., and Kader, A. (2015). Measuring Postharvest Losses in Fruits and Vegetables in Developing Countries, The Postharvest Education Foundation."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2169","DOI":"10.17660\/ActaHortic.2005.682.296","article-title":"Increasing Food Availability by Reducing Postharvest Losses of Fresh Produce","volume":"682","author":"Kader","year":"2005","journal-title":"Acta Hortic."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e02272","DOI":"10.1016\/j.heliyon.2019.e02272","article-title":"Study on Post-Harvest Quantitative and Qualitative Losses of Potato Tubers from Two Different Road Access Districts of Jimma Zone, South West Ethiopia","volume":"5","author":"Kuyu","year":"2019","journal-title":"Heliyon"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.jksuci.2018.06.002","article-title":"Fruits and Vegetables Quality Evaluation Using Computer Vision: A Review","volume":"33","author":"Bhargava","year":"2021","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/S1537-5110(03)00088-6","article-title":"Machine Vision System for Automatic Quality Grading of Fruit","volume":"85","author":"Blasco","year":"2003","journal-title":"Biosyst. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Danielak, M., Przyby\u0142, K., and Koszela, K. (2023). The Need for Machines for the Nondestructive Quality Assessment of Potatoes with the Use of Artificial Intelligence Methods and Imaging Techniques. Sensors, 23.","DOI":"10.3390\/s23041787"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1007\/s11947-011-0725-1","article-title":"Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment","volume":"5","author":"Lorente","year":"2012","journal-title":"Food Bioprocess. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s11947-010-0411-8","article-title":"Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables","volume":"4","author":"Cubero","year":"2011","journal-title":"Food Bioprocess Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep Learning in Agriculture: A Survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0260-8774(03)00183-3","article-title":"Improving Quality Inspection of Food Products by Computer Vision\u2014A Review","volume":"61","author":"Brosnan","year":"2004","journal-title":"J. Food Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.tifs.2018.09.018","article-title":"Challenges and Solutions of Optical-Based Nondestructive Quality Inspection for Robotic Fruit and Vegetable Grading Systems: A Technical Review","volume":"81","author":"Zhang","year":"2018","journal-title":"Trends Food Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fuentes, A., Yoon, S., and Park, D.S. (2019). Deep Learning-Based Phenotyping System with Glocal Description of Plant Anomalies and Symptoms. Front. Plant Sci., 10.","DOI":"10.3389\/fpls.2019.01321"},{"key":"ref_16","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_18","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_19","doi-asserted-by":"crossref","first-page":"108420","DOI":"10.1016\/j.jfca.2025.108420","article-title":"Multi-Task Learning Based Approach for Potato Edibility Detection and Defect Segmentation","volume":"148","author":"Li","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wang, S., Hu, Y., Yang, H., Guo, T., and Yi, X. (2023). Evaluation Method of Potato Storage External Defects Based on Improved U-Net. Agronomy, 13.","DOI":"10.3390\/agronomy13102503"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5725","DOI":"10.1007\/s11042-022-13390-1","article-title":"Potato Diseases Detection and Classification Using Deep Learning Methods","volume":"82","author":"Arshaghi","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, R.-F., and Su, W.-H. (2024). The Application of Deep Learning in the Whole Potato Production Chain: A Comprehensive Review. Agriculture, 14.","DOI":"10.3390\/agriculture14081225"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"108114","DOI":"10.1016\/j.compag.2023.108114","article-title":"From One Field to Another\u2014Unsupervised Domain Adaptation for Semantic Segmentation in Agricultural Robotics","volume":"212","author":"Magistri","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105306","DOI":"10.1016\/j.compag.2020.105306","article-title":"Towards Weeds Identification Assistance through Transfer Learning","volume":"171","author":"Mylonas","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Arzuaga-Ochoa, M.E., Acosta-Coll, M., and Barrios Barrios, M. (2026). The Validation\u2013Deployment Gap in Agricultural Information Systems: A Systematic Technology Readiness Assessment. Informatics, 13.","DOI":"10.3390\/informatics13010014"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"44740","DOI":"10.1038\/s41598-025-28351-5","article-title":"Transfer Learning Models for Wheat Ear Detection on Multi-Source Dataset","volume":"15","author":"Brdar","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Moreno-Alcaide, F., Yousef-Yousef, M., D\u00edaz-Cabrera, J.M., C\u00e1mara-D\u00edaz, L.M., Quesada-Moraga, E., and Ram\u00edrez-Faz, J.C. (2025). Development and Validation of an Image Dataset for Automatic Recognition of the Olive Fruit Fly (Bactrocera oleae) Using Machine Learning. AgriEngineering, 7.","DOI":"10.3390\/agriengineering7120422"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"108833","DOI":"10.1016\/j.rineng.2025.108833","article-title":"From Vineyard to Vision: Multi-Domain Analysis and Mitigation of Grape Cluster Detection Failures in Complex Viticultural Environments","volume":"29","author":"Rana","year":"2026","journal-title":"Results Eng."},{"key":"ref_29","unstructured":"Sapkota, R., Cheppally, R.H., Sharda, A., and Karkee, M. (2025). YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Verk, J., Hernavs, J., and Klan\u010dnik, S. (2025). Using a Region-Based Convolutional Neural Network (R-CNN) for Potato Segmentation in a Sorting Process. Foods, 14.","DOI":"10.3390\/foods14071131"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"473","DOI":"10.2507\/IJSIMM24-3-735","article-title":"The Use of Simulation in Optimization of Airport Baggage Sorting System","volume":"24","author":"Saderova","year":"2025","journal-title":"Int. J. Simul. Model."}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/12\/2121\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T04:16:49Z","timestamp":1781410609000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/12\/2121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":31,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["foods15122121"],"URL":"https:\/\/doi.org\/10.3390\/foods15122121","relation":{},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]}}}