Geometrical and Textural Features Extraction for Honey Plants Pollen Recognition

The aim of the study is to investigate the extraction of features from microscopic images of honey plants pollen for classifying honey based on its botanical origin. Pollens from black locust, linden, lavender, canola and thistle are used. The color image of the pollen grain is converted into a gray image, from which classification features are extracted using popular texture recognition methods - Gabor filter, gray level co-occurrence matrix and local binary patterns. The extracted textural features are then processed with the principal component analysis method for dimensionality reduction and removal of correlated data. Geometric features related to the shape of the pollen grain are extracted from the binarized image. Through linear discriminant analysis, four classifiers are synthesized based on the textural and geometric features. To improve their performance, three hybrid structures mixing textural and geometric features are proposed. A comparative analysis of the performance of all seven linear classifiers is performed using a leave-one-out-cross-validation test. The best success rate obtained is 96%. The efficacy of the proposed algorithms is assessed through simulations conducted using the MATLAB programming language.