P. Carrión, E. Cernadas, P. de Sá Otero, and E. Díaz-Losada (Spain)
Image analysis, Texture classification, Pollen loads
Humans are interested in the knowledge of pollen loads composition due to their nutritional value and therapeutical benefits. Its palynological composition depends on the local flora surrounding the beehive. So, the presence of a specific composition of pollen types in a sample indicates its geographical origin. Currently, pollen origin is manually determined by an expert palynologist counting the proportion of pollen types analyzing the pollen of the hive with an optical microscopy. This procedure is tedious and expensive for its systematic application. We present an automatic methodology to discriminate pollen loads of genus Rubus and Cytisus based on texture image classification. The method consists of three steps: after selection non-blurring regions of interest (ROIs) in the original image, a texture feature vector for each ROIs is calculated, which is used to discriminate between pollen types. An statistical evaluation of the algorithm is provided and discussed.
Important Links:
Go Back
