Article Preview
TopIntroduction
Honey is the natural sweet substance, produced by honey bees from the nectar of plants or from the secretions of living parts of plants or excretions of plant-sucking insects on the living parts of plants, which the bees collect, transform by combining with specific substances of their own, deposit, dehydrate, store and leave in honeycombs to ripen and mature (Codex, 2001).
Identifying the origin of honey and other bee products, such as the pollen and the propolis, can contribute to the development of beekeeping productivity and the revitalization of the region's economy. In the production of apicultural products, Apis mellifera worker bees leave the hive and cover a flight radius of 3 km in search of floral resources. In this process, the pollen grains are attached to the bee and are transported into the hive. Thus, during the analysis of samples of bee products, it is possible to identify the pollen grains present in them, the pollen being an indelible mark of the botanical origin of the product, which directly influences its label of origin (Rodrigues, 2015). Honey pollen analysis, namely melissopalynology that is a science which studies the pollen contained in the honey. The microscopic examination of the honey gives information on its geographical origin and its botanical origin. Melissopalynology allows to control the quality of honeys and in particular to detect frauds and mixtures (Sourava, in press). The pollen analysis method consists of separating the pollen grains from the material around them in order to observe their morphology on a microscopic slide (Von, 2004). However, many botanical species have a similar floral morphology of their pollen grains, this fact complicates the identification process, that is commonly achieved manually by a visual observation on a microscope by a human expert, such analysis techniques are too slow to provide information about identifications of pollen grains, where it can take even months (Kaya, 2013).Over the last few years several machine learning techniques have been developed to detect pollen species in images in order to facilitate the task for the human being, even the automatic identification time of pollen grain images can be reduced from months to hours.
Figure 1 shows the manual pollen recognition process done by biologists, in which the biologist must detect the pollen in the image. This equals to make the segmentation of the image, and is based on the information observed on this pollen namely: the morphology or the form, the pores and grooves whose number and the provision differ from one species to another. The difficulty is that many botanical species has a close floral morphology which makes the processes of the pollen recognition very difficult for the human.
Figure 1. Manual pollen recognition process done by biologists