{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:54:27Z","timestamp":1774450467660,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Melissopalynological analysis is essential for determining the botanical origin of honey, corbicular pollen and bee bread, as well as detecting adulteration. However, it traditionally relies on labor-intensive and subjective manual pollen identification. As a proof-of-concept preceding full honey analysis, this study evaluates artificial intelligence methods for automated pollen grain recognition under controlled conditions. Hazel (Corylus avellana L.) and dandelion (Taraxacum officinale F.H. Wigg.) were used as model taxa to validate the proposed approach before its application to real varietal honey samples. This study introduces a novel three-stage pipeline that decouples object detection from feature extraction, utilizing YOLOv12m for region-of-interest generation and, for the first time in melissopalynology, DINOv3 ConvNeXt-B for deep feature representation. Microscopic images acquired at 400\u00d7 magnification yielded 2498 dandelion and 1941 hazel pollen grains. The detector achieved an mAP@0.5 of 0.936 with an F1 score of 0.88, while the classifier reached 98.1% accuracy with good class separability (Silhouette coefficient: 0.407). The primary technical contribution is the systematic optimization of the detection-to-classification interface. Context-aware bounding box expansion (12%) and an optimized IoU-NMS threshold (0.65) significantly improve the stability of morphological feature extraction, as confirmed by ablation studies. Computational cost reporting further supports reproducible, deployment-oriented comparison. The results confirm the feasibility of this AI-based framework as an intermediate step toward automated melissopalynological analysis, with future work focusing on standardized microscopy protocols and expanded pollen databases for varietal honey authentication.<\/jats:p>","DOI":"10.3390\/s26072043","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T13:57:34Z","timestamp":1774447054000},"page":"2043","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Preliminary Research on the Possibility of Automating the Identification of Pollen Grains in Melissopalynology Using AI, with Particular Emphasis on Computer Image Analysis Methods"],"prefix":"10.3390","volume":"26","author":[{"given":"Kacper","family":"Litwi\u0144czyk","sequence":"first","affiliation":[{"name":"Department of Geodesy, Institute of Geodesy and Civil Engineering, Faculty of Geoengineering, University of Warmia and Mazury in Olsztyn, 10-719 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micha\u0142","family":"Podralski","sequence":"additional","affiliation":[{"name":"Department of Geodesy, Institute of Geodesy and Civil Engineering, Faculty of Geoengineering, University of Warmia and Mazury in Olsztyn, 10-719 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulina","family":"Skorynko","sequence":"additional","affiliation":[{"name":"Department of Poultry Science and Apiculture, Faculty of Animal Bioengineering, University of Warmia and Mazury in Olsztyn, Sloneczna 48, 10-957 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8175-5115","authenticated-orcid":false,"given":"Ewa","family":"Malinowska","sequence":"additional","affiliation":[{"name":"Department of Poultry Science and Apiculture, Faculty of Animal Bioengineering, University of Warmia and Mazury in Olsztyn, Sloneczna 48, 10-957 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuzanna","family":"Czarnota","sequence":"additional","affiliation":[{"name":"Department of Poultry Science and Apiculture, Faculty of Animal Bioengineering, University of Warmia and Mazury in Olsztyn, Sloneczna 48, 10-957 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beata","family":"B\u0105k","sequence":"additional","affiliation":[{"name":"Department of Poultry Science and Apiculture, Faculty of Animal Bioengineering, University of Warmia and Mazury in Olsztyn, Sloneczna 48, 10-957 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-408X","authenticated-orcid":false,"given":"Artur","family":"Janowski","sequence":"additional","affiliation":[{"name":"Department of Geodesy, Institute of Geodesy and Civil Engineering, Faculty of Geoengineering, University of Warmia and Mazury in Olsztyn, 10-719 Olsztyn, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"ref_1","unstructured":"Hyde, H.A., and Williams, D.A. (1955). A Synoptic Guide to the Study of Pollen, University College of South Wales and Monmouthshire."},{"key":"ref_2","unstructured":"Obigba, S.O. (2022). Understanding Past and Present Vegetation Dynamics Using the Palynological Approach: An Introductory Discourse. Vegetation Index and Dynamics, IntechOpen."},{"key":"ref_3","first-page":"88","article-title":"History of melissopalynological methods","volume":"27","author":"Gencay","year":"2018","journal-title":"Commun. Fac. Sci. Univ. Ank. Ser. C Biol. Geol. Eng. Geophys. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"53","DOI":"10.14483\/udistrital.jour.colomb.for.2013.1.a04","article-title":"El polen ap\u00edcola como producto forestal no maderable en la Cordillera Oriental de Colombia","volume":"16","author":"Bonilla","year":"2013","journal-title":"Colomb. For."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"449","DOI":"10.31055\/1851.2372.v51.n3.15390","article-title":"An\u00e1lisis pol\u00ednico de mieles inmaduras en el sector oeste de las yungas de Jujuy (Argentina)","volume":"51","author":"Mendez","year":"2016","journal-title":"Bolet\u00edn Soc. Argent. Bot\u00e1nica"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Rostami, M.A., Kydd, L., Balmaki, B., Dyer, L.A., and Allen, J.M. (2025). Deep learning for accurate classification of conifer pollen grains: Enhancing species identification in palynology. Front. Big Data, 8.","DOI":"10.3389\/fdata.2025.1507036"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/0034-6667(90)90133-4","article-title":"Computerized identification of pollen grains by texture analysis","volume":"64","author":"Langford","year":"1990","journal-title":"Rev. Palaeobot. Palynol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gon\u00e7alves, A.B., Souza, J.S., da Silva, G.G., Cereda, M.P., Pott, A., Naka, M.H., and Pistori, H. (2016). Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0157044"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Balmaki, B., Rostami, M.A., Christensen, T., Leger, E.A., Allen, J.M., Feldman, C.R., Forister, M.L., and Dyer, L.A. (2022). Modern approaches for leveraging biodiversity collections to understand change in plant-insect interactions. Front. Ecol. Evol., 10.","DOI":"10.3389\/fevo.2022.924941"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mateo, F., Tarazona, A., and Mateo, E.M. (2021). Comparative Study of Several Machine Learning Algorithms for Classification of Unifloral Honeys. Foods, 10.","DOI":"10.3390\/foods10071543"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"H\u00fcsrevo\u011flu, M., Janowski, A., and Kark\u0131nl\u0131, A.E. (2025). Optimizing Vehicle Placement in the Residual Spaces of Unmarked Parking Areas: A Comparative Study of Heuristic Methods. Appl. Sci., 15.","DOI":"10.3390\/app15126416"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ahmed, E. (2024). Detection of honey adulteration using machine learning. PLoS Digit. Health, 3.","DOI":"10.1371\/journal.pdig.0000536"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, X., and Ju, F. (2022). Automatic Classification of Pollen Grain Microscope Images Using a Multi-Scale Classifier with SRGAN Deblurring. Appl. Sci., 12.","DOI":"10.3390\/app12147126"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1111\/2041-210X.13575","article-title":"Efficient, automated and robust pollen analysis using deep learning","volume":"12","author":"Olsson","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s00704-025-05637-2","article-title":"Evaluating the performance of ANN and ANFIS models for spatial precipitation prediction in complex terrain: A case study in central Anatolia","volume":"156","author":"Husrevoglu","year":"2025","journal-title":"Theor. Appl. Climatol."},{"key":"ref_16","first-page":"101665","article-title":"YOLOv8-based on-the-fly classifier system for pollen analysis of Guindo Santo (Eucryphia glutinosa) honey and assessment of its monoflorality","volume":"19","author":"Jofre","year":"2025","journal-title":"J. Agric. Food Res."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Janowski, A., H\u00fcsrevo\u011flu, M., and Renigier-Bilozor, M. (2024). Sustainable Parking Space Management Using Machine Learning and Swarm Theory\u2014The SPARK System. Appl. Sci., 14.","DOI":"10.3390\/app142412076"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1111\/nph.19857","article-title":"A user-friendly method to get automated pollen analysis from environmental samples","volume":"243","author":"Gimenez","year":"2024","journal-title":"New Phytol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kubera, E., Kubik-Komar, A., Kurasi\u0144ski, P., Piotrowska-Weryszko, K., and Skrzypiec, M. (2022). Detection and Recognition of Pollen Grains in Multilabel Microscopic Images. Sensors, 22.","DOI":"10.3390\/s22072690"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kubicki, B., Janowski, A., and Inglot, A. (2025). Multimodal Augmented Reality System for Real-Time Roof Type Recognition and Visualization on Mobile Devices. Appl. Sci., 15.","DOI":"10.3390\/app15031330"},{"key":"ref_21","first-page":"104229","article-title":"UAV measurements and AI-driven algorithms fusion for real estate good governance principles support","volume":"134","author":"Tysiac","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_22","unstructured":"HumanSignal (2026, March 01). Label-Studio. Available online: https:\/\/github.com\/HumanSignal\/label-studio."},{"key":"ref_23","unstructured":"Ivder (2026, March 01). YoloBBoxChecker. Available online: https:\/\/github.com\/ivder\/YoloBBoxChecker."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_25","unstructured":"Ben-Yosef, M., and Weinshall, D. (2018). Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104523","DOI":"10.1016\/j.compbiomed.2021.104523","article-title":"A survey on applications of deep learning in microscopy image analysis","volume":"134","author":"Liu","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.","DOI":"10.3390\/info11020125"},{"key":"ref_28","unstructured":"Perez, L., and Wang, J. (2017). The Effectiveness of Data Augmentation in Image Classification using Deep Learning. arXiv."},{"key":"ref_29","unstructured":"Sim\u00e9oni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khalidov, V., Szafraniec, M., Yi, S., and Ramamonjisoa, M. (2025). DINOv3. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_31","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, X., Deng, L., Hu, C., Xie, T., and Wang, C. (2024). Dense Small Object Detection Based on an Improved YOLOv7 Model. Appl. Sci., 14.","DOI":"10.3390\/app14177665"},{"key":"ref_33","unstructured":"Huang, S., Hou, Y., Liu, L., Yu, X., and Shen, X. (2025). Real-Time Object Detection Meets DINOv3. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., and Philbin, J. (2015). FaceNet: A Unified Embedding for Face Recognition and Clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref_35","first-page":"169","article-title":"Unsupervised Embedding Quality Evaluation","volume":"221","author":"Tsitsulin","year":"2023","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_37","unstructured":"Van Rijsbergen, C.J. (1979). Information Retrieval, Butterworths."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Davis, J., and Goadrich, M. (2006). The Relationship between Precision-Recall and ROC Curves. Proceedings of the 23rd International Conference on Machine Learning\u2014ICML \u201906, ACM Press.","DOI":"10.1145\/1143844.1143874"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The Pascal Visual Object Classes Challenge: A Retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1162\/coli.2009.35.2.307","article-title":"Introduction to Information Retrieval","volume":"35","author":"Vechtomova","year":"2009","journal-title":"Comput. Linguist."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., and Doll\u00e1r, P. (2014). Microsoft COCO: Common Objects in Context. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/S0034-4257(97)00083-7","article-title":"Selecting and interpreting measures of thematic classification accuracy","volume":"62","author":"Stehman","year":"1997","journal-title":"Remote Sens. Environ."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil, A., and Caruana, R. (2005). Predicting Good Probabilities with Supervised Learning. Proceedings of the 22nd International Conference on Machine Learning\u2014ICML \u201905, ACM Press.","DOI":"10.1145\/1102351.1102430"},{"key":"ref_44","first-page":"1321","article-title":"On Calibration of Modern Neural Networks","volume":"70","author":"Guo","year":"2017","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shi, X., Hou, G., Wang, F., and Li, H. (2026). Pollen-YOLO: A Deep Learning Framework for Automated Pollen Identification and Its Application to Palaeoecological Reconstruction on the Tibetan Plateau. Quaternary, 9.","DOI":"10.3390\/quat9010006"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Wu, J., Kuang, Z., Wang, L., Zhang, W., and Wu, G. (2020). Context-Aware RCNN: A Baseline for Action Detection in Videos. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"11627","DOI":"10.1007\/s00521-021-05867-1","article-title":"Global Context Aware RCNN for Object Detection","volume":"33","author":"Zhang","year":"2021","journal-title":"Neural Comput. Appl."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2043\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T13:59:54Z","timestamp":1774447194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":47,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072043"],"URL":"https:\/\/doi.org\/10.3390\/s26072043","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]}}}