Pollen-grains recognition using classical methods and neural networks

This paper describes the problem of automated pollen-grains image recognition using images from microscope. This problem is relevant because it can help to automate a complex process of pollen-grains classification and to determine the beginning of plants pollinating which are cause of allergy. The main recognition method is Hamming network and linguistic approach. The paper includes Hamming network advantages over Hopfield network. The step of preprocessing (noise filtering, binarization, segmentation) uses OpenCV functions and the feature point method. The paper describes both preprocessing algorithms and main recognition methods. The experiments results showed relative efficiency of these methods. The conclusions about methods productivity are based on errors of type I and II. The paper includes alternative recognition methods which are planning to use in the follow up researches