Authentication of bee pollen grains in bright-field microscopy by combining one-class classification techniques and image processing

Bee Bread as a Promising Source of Bioactive Molecules and Functional Properties: An Up-to-Date Review

Bee bread is a natural product obtained from the fermentation of bee pollen mixed with bee saliva and flower nectar inside the honeycomb cells of a hive. Bee bread is considered a functional product, having several nutritional virtues and various bioactive molecules with curative or preventive effects. This paper aims to review current knowledge regarding the chemical composition and medicinal properties of bee bread, evaluated in vitro and in vivo, and to highlight the benefits of the diet supplementation of bee bread for human health. Bee bread extracts (distilled water, ethanol, methanol, diethyl ether, and ethyl acetate) have been proven to have antioxidant, antifungal, antibacterial, and antitumoral activities, and they can also inhibit α-amylase and angiotensin I-converting enzyme in vitro. More than 300 compounds have been identified in bee bread from different countries around the world, such as free amino acids, sugars, fatty acids, minerals, organic acids, polyphenols, and vitamins. In vivo studies have revealed the efficiency of bee bread in relieving several pathological cases, such as hyperglycemia, hyperlipidemia, inflammation, and oxidative stress.

Combating data incompetence in pollen images detection and classification for pollinosis prevention

Automatic pollen images recognition is crucial for pollinosis symptoms prevention and treatment. The problem of pollen recognition can be efficiently solved using deep learning, however neural networks require tens of thousands of images to generalize. At the same time, the existing open pollen images datasets are very small. In this paper, we present a novel open pollen dataset annotated for both detection and classification tasks. Based on our dataset we study learning from a small data using different state-of-the-art approaches. For the detection task we propose to use our new Bayesian RetinaNet network, which models aleatoric uncertainty. We compare it with the baseline RetinaNet and demonstrate that our model allows for higher detection precision. For the classification task we compare the impact of pre-training on the synthetic images from generative adversarial networks (GANs) and metric-based few-shot learning. Namely, we pre-trained our small convolutional neural network and Siamese neural network classifiers on synthetic pollen images generated by two GANs: StyleGAN and Self-attention GAN. The best classifier is the convolutional neural network pre-trained on StyleGAN images. Our best models achieved 96.3% of mean average precision for the detection task and 97.7% of F1 measure for the classification task on 13 pollen plant species. We have implemented the best models in our pollen recognition web service, which is available for palynologists on request.

Identification of pollen taxa by different microscopy techniques

Melissopalynology is an important analytical method to identify botanical origin of honey. Pollen grain recognition is commonly performed by visual inspection by a trained person. An alternative method for visual inspection is automated pollen analysis based on the image analysis technique. Image analysis transfers visual information to mathematical descriptions. In this work, the suitability of three microscopic techniques for automatic analysis of pollen grains was studied. 2D and 3D morphological characteristics, textural and colour features, and extended depth of focus characteristics were used for the pollen discrimination. In this study, 7 botanical taxa and a total of 2482 pollen grains were evaluated. The highest correct classification rate of 93.05% was achieved using the phase contrast microscopy, followed by the dark field microscopy reaching 91.02%, and finally by the light field microscopy reaching 88.88%. The most significant discriminant characteristics were morphological (2D and 3D) and colour characteristics. Our results confirm the potential of using automatic pollen analysis to discriminate pollen taxa in honey. This work provides the basis for further research where the taxa dataset will be increased, and new descriptors will be studied.

Spectroscopic Discrimination of Bee Pollen by Composition, Color, and Botanical Origin

Bee pollen samples were discriminated using vibrational spectroscopic methods by connecting with botanical sources, composition, and color. SEM and light microscope images of bee pollen loads were obtained and used to assess the botanical origin. Fourier transform (FT) mid- and near-infrared (FT-MIR, FT-NIR), and FT-Raman spectra of bee pollen samples (a set of randomly chosen loads can be defined as an independent sample) were measured and processed by principal component analysis (PCA). The CIE L*a*b* color space parameters were calculated from the image analysis. FT-MIR, FT-NIR, and FT-Raman spectra showed marked sensitivity to bee pollen composition. In addition, FT-Raman spectra indicated plant pigments as chemical markers of botanical origin. Furthermore, the fractionation of bee pollen was also performed, and composition of the fractions was characterized as well. The combination of imaging, spectroscopic, and statistical methods is a potent tool for bee pollen discrimination and thus may evaluate the quality and composition of this bee-keeping product.

Improving classification of pollen grain images of the POLEN23E dataset through three different applications of deep learning convolutional neural networks

In palynology, the visual classification of pollen grains from different species is a hard task which is usually tackled by human operators using microscopes. Its complete automatization would save a high quantity of resources and provide valuable improvements especially for allergy-related information systems, but also for other application fields as paleoclimate reconstruction, quality control of honey based products, collection of evidences in criminal investigations or fabric dating and tracking. This paper presents three state-of-the-art deep learning classification methods applied to the recently published POLEN23E image dataset. The three methods make use of convolutional neural networks: the first one is strictly based on the idea of transfer learning, the second one is based on feature extraction and the third one represents a hybrid approach, combining transfer learning and feature extraction. The results from the three methods are indeed very good, reaching over 97% correct classification rates in images not previously seen by the models, where other authors reported around 70.