Identifying the botanical origin of honey is essential for ensuring its quality, preventing adulteration, and protecting consumers. Traditional techniques, such as melissopalynology, physicochemical analysis, and PCR, are often labor-intensive, time-consuming, or limited to the detection of only known species, while advanced DNA sequencing remains prohibitively costly. In this study, we aim to develop a deep learning-based approach for identifying pollen grains extracted from honey and captured through microscopic imaging. To achieve this, we first constructed a dataset named VNUA-Pollen52, which consists of microscopic images of pollen grains collected from flowers of plant species cultivated in the surveyed area in Hanoi, Vietnam. Second, we evaluated the classification performance of advanced deep learning models, including MobileNet, YOLOv11, and Vision Transformer, on pollen grain images. To improve performances of these model, we proposed data augmentation and hybrid fusion strategies to improve the identification accuracy of pollen grains extracted from honey. Third, we developed an online platform to support experts in identifying these pollen grains and to gather expert consensus, ensuring accurate determination of the plant species and providing a basis for evaluating the proposed identification strategy. Experimental results on 93 images of pollen grains extracted from honey samples demonstrated the effectiveness of the proposed hybrid fusion strategy, achieving 70.21% accuracy at rank 1 and 92.47% at rank 5. This study demonstrates the capability of recent advances in computer vision to identify pollen grains using their microscopic images, thereby opening up opportunities for the development of automated systems that support plant traceability and quality control of honey.

Bee counting is an essential task for monitoring the health of bee colonies. However, it is challenging, as bees are often small and difficult to see. One approach to bee counting is detecting individuals and using that information to count. However, this approach can be unreliable if the data are noisy, meaning some labels are incorrect. This paper presents a novel approach to bee counting with noise-labeled data. The proposed method uses a density-based counter that is robust with noisy data. Experimental results show that the proposed method can achieve significantly higher accuracy than the detection-based approach for bee counting with noise-labeled data. The proposed method can improve the accuracy of bee counting in various scenes, such as different weather conditions and the density of bees. The approach could also be used to develop new tools for monitoring bee populations. Source codes of the proposed method and the dataset are publicly available on GitHub.