An expert diagnosis system for classification of human parasite eggs based on multi class svm

In this paper, it is proposed a new methodology based on invariant moments and Multi Class Support Vector Machine (MCSVM) for classification of human parasite eggs in microscopic images. These are pre-processing stage, feature extraction stage, classification stage, and testing stage. In pre-processing stage, the digital image processing methods, which are noise reduction, contrast enhancement, thresholding, and morphological and logical processes. In feature extraction stage, the invariant moments of pre-processed parasite images are calculated. Finally, in classification stage, the Multi Support Vector Machine (MSVM) classifier is used for classification of features extracted feature extraction stage. A 93.49 % correct recognition rate is obtained when employing the ANFIS structure on the same parasite cell images and feature vector, on the other hand, in this thesis the employed IM-MSVM structure obtained a 97.7 % correct classification rate. With this study, it is seen that IM-MSVM system has the ability of diagnosing the parasitic diseases well enough.