{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:30:57Z","timestamp":1787938257676,"version":"build-2784847793"},"reference-count":32,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T00:00:00Z","timestamp":1776470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"IEETA\/LASI Portugal","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Old-vine vineyards often contain dozens of grapevine varieties intermingled and irregularly distributed, making plant-level varietal identification slow and expensive when based on ampelography or molecular approaches. This paper proposes a field-oriented computer-vision pipeline for Vitis vinifera variety identification using images with a natural background from the historic \u201cVinha Maria Teresa\u201d parcel (Quinta do Crasto, Portugal). A single-class YOLO11 detector is trained to localize the vine leaf and generate standardized crops, and a YOLO11 classifier is then fine-tuned on leaf regions of interest (ROIs) for eight selected varieties in the Douro UNESCO region. We annotated 2015 vineyard images for classification and supplemented detection training with 2648 additional leaf images; detectors (YOLO11n\/s\/m) were benchmarked under four augmentation regimes and evaluated on a fixed 48-image subset, including runtime on CPU and GPU. The best detector reached mAP@50\u201395 of 0.918 on the benchmark, while YOLO11n achieved \u223c27 FPS on CPU for fast cropping. On a 303-image test set, the best classifier (YOLO11s with mixed augmentations) achieved 94.06% Top-1 accuracy, 93.92% macro-F1, and 100% Top-5 accuracy with remaining errors concentrated among morphologically similar varieties. To assess deployment-oriented performance, classifiers trained under three input settings (manual crops, detector-generated crops, and full images) were evaluated on a held-out 48-image benchmark subset; removing the detection step reduced Top-1 accuracy from 75.00% to 68.75%, while the gap between manual and automatic crops was only 2.44 pp on successfully detected images with detection failures (14.6%) representing the primary operational bottleneck. Repeated retraining of the best manual-crop YOLO11s configuration across multiple random seeds showed stable performance with low variability in Top-1 accuracy and macro-F1. Under identical training conditions, ResNet50 and EfficientNet-B0 provided competitive baselines, but YOLO11s remained the strongest overall model on the held-out field benchmark. These results indicate that lightweight leaf detection plus crop-based classification can support scalable varietal identification in old vineyards under realistic acquisition conditions.<\/jats:p>","DOI":"10.3390\/make8040106","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T07:15:08Z","timestamp":1776669308000},"page":"106","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["vinum-Analytics"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4104-6573","authenticated-orcid":false,"given":"Nuno","family":"Ferreira","sequence":"first","affiliation":[{"name":"Engineering Department, School of Science and Technology, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8708-9025","authenticated-orcid":false,"given":"Filipe","family":"Pinto","sequence":"additional","affiliation":[{"name":"Altice Labs, 3810-106 Aveiro, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5798-1298","authenticated-orcid":false,"given":"Ant\u00f3nio","family":"Valente","sequence":"additional","affiliation":[{"name":"Engineering Department, School of Science and Technology, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"INESC TEC\u2014INESC Technology and Science, 4200-465 Porto, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6814-9217","authenticated-orcid":false,"given":"Diana","family":"Augusto","sequence":"additional","affiliation":[{"name":"Quinta do Crasto, 5060-063 Sabrosa, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6682-0460","authenticated-orcid":false,"given":"Manuela","family":"Reis","sequence":"additional","affiliation":[{"name":"Engineering Department, School of Science and Technology, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5862-5706","authenticated-orcid":false,"given":"Salviano","family":"Soares","sequence":"additional","affiliation":[{"name":"Engineering Department, School of Science and Technology, University of Tr\u00e1s-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal"},{"name":"Institute of Electronics and Informatics Engineering of Aveiro (IEETA)\/Intelligent Systems Associate Laboratory (LASI), University of Aveiro, 3810-193 Aveiro, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,18]]},"reference":[{"key":"ref_1","unstructured":"(2026, February 16). Douro\/Porto, Available online: https:\/\/www.ivv.gov.pt\/np4\/77\/."},{"key":"ref_2","unstructured":"Instituto da Vinha e do Vinho, I. P. (2024). Vinhos e Aguardentes de Portugal 2024: Anu\u00e1rio, Instituto da Vinha e do Vinho, I. P."},{"key":"ref_3","unstructured":"Voss, R. (2026, February 27). Centuries of Tradition Have Shaped Portugal\u2019s Douro Valley, 2025\u2019s International Wine Region of the Year. Wine Enthusiast. Available online: https:\/\/www.wineenthusiast.com\/culture\/industry-news\/wine-star-awards\/international-wine-region-2025\/."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sousa, B., Ara\u00fajo, S.d.S., Sales, H., Pontes, R., and Nunes, J. (2024). Douro Vineyards: A Perspective for the Valorization and Conservation of Grapevine Genetic Resources. Agronomy, 14.","DOI":"10.3390\/agronomy14020245"},{"key":"ref_5","unstructured":"(2025, October 02). Characteristics of the Region. Available online: https:\/\/www.ivdp.pt\/en\/viticulture\/region\/characteristics-of-the-region\/."},{"key":"ref_6","unstructured":"Instituto dos Vinhos do Douro e do Porto, I. P (2025, October 07). Circular n. \u00ba 11\/2020: Cria\u00e7\u00e3o da Men\u00e7\u00e3o \u201cVinhas Velhas\u201d, Para Utiliza\u00e7\u00e3o na Rotulagem dos Vinhos DOP Porto, DOP Douro e IGP Duriense. Available online: https:\/\/www.ivdp.pt\/pt\/agentes-economicos\/circulares\/."},{"key":"ref_7","unstructured":"(2025, September 29). Old vines in the Douro: The Heritage, the Commitment. Available online: https:\/\/www.oldvines.org\/blog\/old-vines-douro."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Augusto, D., Ib\u00e1\u00f1ez, J., Pinto-Sintra, A.L., Falco, V., Leal, F., Mart\u00ednez-Zapater, J.M., Oliveira, A.A., and Castro, I. (2021). Grapevine Diversity and Genetic Relationships in Northeast Portugal Old Vineyards. Plants, 10.","DOI":"10.3390\/plants10122755"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"111826","DOI":"10.1016\/j.scienta.2023.111826","article-title":"Identification of Portuguese traditional grapevines using molecular marker-based strategies","volume":"311","author":"Barrias","year":"2023","journal-title":"Sci. Hortic."},{"key":"ref_10","unstructured":"(2026, January 11). Quinta do Crasto Vinha Maria Teresa. Available online: https:\/\/www.quintadocrasto.wine\/en\/products\/quinta-crasto-vinha-maria-teresa\/."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"109675","DOI":"10.1016\/j.compag.2024.109675","article-title":"Advancing digital ampelography: Automated classification of grapevine varieties","volume":"229","author":"Shahrabadi","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1104\/pp.113.229708","article-title":"A modern ampelography: A genetic basis for leaf shape and venation patterning in grape","volume":"164","author":"Chitwood","year":"2014","journal-title":"Plant Physiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1007\/s00122-004-1760-3","article-title":"Development of a standard set of microsatellite reference alleles for identification of grape cultivars","volume":"109","author":"This","year":"2004","journal-title":"Theor. Appl. Genet."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4851","DOI":"10.3390\/agriengineering6040277","article-title":"Advancing Grapevine Variety Identification: A Systematic Review of Deep Learning and Machine Learning Approaches","volume":"6","author":"Carneiro","year":"2024","journal-title":"AgriEngineering"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1007\/s00122-010-1527-y","article-title":"High throughput analysis of grape genetic diversity as a tool for germplasm collection management","volume":"122","author":"Laucou","year":"2011","journal-title":"Theor. Appl. Genet."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.compag.2013.08.021","article-title":"Identification of grapevine varieties using leaf spectroscopy and partial least squares","volume":"99","author":"Diago","year":"2013","journal-title":"Comput. Electron. Agric."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"129","DOI":"10.20870\/oeno-one.2021.55.4.4508","article-title":"Ampelographic and molecular characterisation of grapevine varieties in the gene bank of the experimental vineyard \u2018Radmilovac\u2019\u2013Serbia","volume":"55","year":"2021","journal-title":"OENO One"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"110368","DOI":"10.1016\/j.foodcont.2024.110368","article-title":"High resolution melting analysis of microsatellite markers applied to grapevine varietal fingerprinting throughout the wine production chain","volume":"160","author":"Barrias","year":"2024","journal-title":"Food Control"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.asoc.2018.07.059","article-title":"Assessment of grapevine variety discrimination using stem hyperspectral data and AdaBoost of random weight neural networks","volume":"72","author":"Fernandes","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pereira, C.S., Morais, R., and Reis, M.J.C.S. (2019). Deep learning techniques for grape plant species identification in natural images. Sensors, 19.","DOI":"10.3390\/s19224850"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Carneiro, G., P\u00e1dua, L., Sousa, J.J., Peres, E., Morais, R., and Cunha, A. (2021). Grapevine Variety Identification Through Grapevine Leaf Images Acquired in Natural Environment. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE.","DOI":"10.1109\/IGARSS47720.2021.9555141"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1016\/j.procs.2021.12.025","article-title":"Analyzing the Fine Tuning\u2019s impact in Grapevine Classification","volume":"196","author":"Carneiro","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Carneiro, G., Neto, A., Teixeira, A., Cunha, A., and Sousa, J. (2023). Evaluating Data Augmentation for Grapevine Varieties Identification. Proceedings of the IGARSS 2023\u20142023 IEEE International Geoscience and Remote Sensing Symposium, IEEE.","DOI":"10.1109\/IGARSS52108.2023.10283128"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"01021","DOI":"10.1051\/bioconf\/202411701021","article-title":"Vitis Vinera L. Leaf Detection using Faster R-CNN","volume":"117","author":"Sarosa","year":"2024","journal-title":"BIO Web Conf."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Peng, J., Ouyang, C., Peng, H., Hu, W., Wang, Y., and Jiang, P. (2024). MultiFuseYOLO: Redefining Wine Grape Variety Recognition through Multisource Information Fusion. Sensors, 24.","DOI":"10.3390\/s24092953"},{"key":"ref_26","unstructured":"Ultralytics (2026, February 25). Ultralytics YOLO11. Ultralytics YOLO Docs. Available online: https:\/\/docs.ultralytics.com\/models\/yolo11\/."},{"key":"ref_27","unstructured":"Chapman, P. (2026, April 11). CRISP-DM 1.0: Step-by-Step Data Mining Guide. Available online: https:\/\/api.semanticscholar.org\/CorpusID:59777418."},{"key":"ref_28","unstructured":"Vlah, M. (2025, February 26). Grapevine Leaves. Available online: https:\/\/www.kaggle.com\/ds\/1248678."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110425","DOI":"10.1016\/j.measurement.2021.110425","article-title":"A CNN-SVM study based on selected deep features for grapevine leaves classification","volume":"188","author":"Koklu","year":"2022","journal-title":"Measurement"},{"key":"ref_30","unstructured":"(2026, February 25). Roboflow, Inc. Available online: https:\/\/roboflow.com\/about."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","first-page":"6105","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","volume":"97","author":"Tan","year":"2019","journal-title":"Proc. Mach. Learn. Res."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/4\/106\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T04:34:09Z","timestamp":1777005249000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/4\/106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,18]]},"references-count":32,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["make8040106"],"URL":"https:\/\/doi.org\/10.3390\/make8040106","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,18]]}}}