Article Preview
TopIntroduction
Image analysis systems now have an important and all-ever original place, first because they have proved their interest in areas such as image restoration or three-dimensional vision, but also because they are being justified in other previously unexplored areas such as diagnostic assistance. Moreover, the image represents one of the richest sources of information. Because of the variety of possibilities that this information offers, in a myriad of areas, there has been a great deal of enthusiasm for research in the field of computer vision, especially since the advent of digital images. In this regard, Numerous researches has been carried out in this field, and remains one of the most studied areas. There are basically two levels of automatic image processing. The first is a low-level treatment dedicated to acquisition, compression, segmentation, improvement or restoration. The second level is a high-level processing dedicated to symbolic image analysis operations, such as description, recognition or interpretation, in order to extract information (Benaichouche, 2014).Melissopalynology or pollen analysis of honey is one of the areas that benefited greatly from image processing and analysis techniques, where melissopalynology is the science that studies the pollen contained in honey, using a microscopic examination (Yang, 2014).In several palynology research, scientists interested in studying the distribution of pollen species, by studying the spectrogram of pollen developed for a given region from the results of several samples, to determine the botanical and geographical origin of honey, and to control the quality of honey and in particular to detect fraud and mixtures (Louveaux, 1970).Nevertheless, the identification process may be complicated because of the floral morphological similarity of many plant species, this process is more often realize manually by human expert through a visual observation on a microscope. In addition, the manual classification can be expensive to acquire for a human being because of particular physical constraints being concentration and the time required for a large volume of image data. Therefore, this process can take even months (Flenley, 1968). And because of the hardness of to the manual counting pollen and the increased use of applications of palynology, the requirement for a pollen recognition automation has become an evidence. Then in this regard, palynologists can simply take a screenshot of images observed in the microscope based on visualization system and machine learning techniques, and they can reduce time from months to hours (Scharring, 2006). Figure 1 shows the manual pollen recognition process done by biologists, in which the biologist must detect in the image the pollen which 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 differs from one species to another. The difficulty is that many botanical species has a similar floral morphology which makes the processes of the pollen recognition very difficult for the human.
Figure 1.
Manual pollen recognition process done by biologists