Search Results (4)

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× 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. Full article

The environment significantly impacts the lives of bees and their feeding. This study aimed to investigate bee foraging using melissopalynological analysis and DNA metabarcoding in intensive farming, reserved, and urbanized areas. The highest alpha diversity was observed in the reserved and intensive farming areas. The urbanized area had less diversity. In the intensive farming area, Sinapis, Helianthus, and Fagopyrum predominated; in the reserved area, Melilotus, Helianthus, and Brassica predominated. In the urbanized area, garden plants, namely radish (Raphanus sativus) and cucumber (Cucumis hystrix), and agricultural plants, namely soybean (Glycine max) and melon (Cucumis melo), were often found. The most significant agreement was between the rbcL and the melissopalynological analysis. The ITS2 revealed equal matches with both rbcL and melissopalynology, but this marker missed or underestimated some genera. Trifolium pretense and Brassica nigra were identified simultaneously by the melissopalinology method and two genetic markers in DNA metabarcoding. The species Convolvulus arvensis, Melilotus officinalis, Echium vulgare, Brassica rapa, Helianthus divaricatus, and Onobrychis viciifolia were found in all ecological areas. Imperfect databases impose some limits in the identification of some taxa using metabarcoding. The further research and expansion of plant databases is needed. Studying the food preferences of bees in different environmental conditions and landscapes is necessary to develop measures to preserve their populations. Full article

Natural bee honeys are commonly used by patients for nutritional, preventive, and curative purposes. Honey varieties produced in other countries, including Italy and Spain, are gaining popularity. The aim of the study was to evaluate selected antioxidant properties of honey, taking into account the declared and actual variety. The research material consisted of 105 honey samples, including honeys from Poland (n = 50), from Spain (n = 35), and from Italy (n = 20). The variety was determined by the melissopalinological method, and in the case of honeydew honeys, the electrical conductivity was measured. Total phenolic content (TPC), color intensity, color in Pfund scale, DPPH, and FRAP were assessed. Polish buckwheat honeys, with confirmed botanical origin, are characterized by the highest median of the TPC (213.05 mg GAE/100 g), the highest color intensity (1.138 mAU), and the highest value in the FRAP test (0.394 µM Fe²⁺/mL). In conclusion, proper labeling of bee honeys is necessary so as not to mislead consumers, and buckwheat honeys from Poland can be recommended to patients for prophylactic purposes in order to provide antioxidants in the diet. Full article

Pollen analysis and the classification of several pollen species is an important task in melissopalynology. The development of machine learning or deep learning based classification models depends on available datasets of pollen grains from various plant species from around the globe. In this paper, Cretan Pollen Dataset v1 (CPD-1) is presented, which is a novel dataset of grains from 20 pollen species from plants gathered in Crete, Greece. The pollen grains were prepared and stained with fuchsin, in order to be captured by a camera attached to a microscope under a $\times 400$ magnification. In addition, a pollen grain segmentation method is presented, which segments and crops each unique pollen grain and achieved an overall detection accuracy of 92%. The final dataset comprises 4034 segmented pollen grains of 20 different pollen species, as well as the raw data and ground truth, as annotated by an expert. The developed dataset is publicly accessible, which we hope will accelerate research in melissopalynology. Full article