Automatic Malaria Detection Technique Using ANN Classifiers

Abstract

Malaria is a serious infectious disease. According to the World Health Organization, it accounts for almost one million deaths per year. The manual microscopy is now considered as the gold standard for diagnosing the malaria. Due to the number of steps required in manual assessment, this diagnostic method is time-consuming and susceptible to human error resulting in a misdiagnosed diagnosis. The proposed system focuses on the advanced malaria detection technique using Artificial Neural Network Classification. This method uses the Intensity characteristics of Plasmodium parasites to find the infected and uninfected erythrocytes. The images of the erythrocytes are acquired, pre-processed, relevant features get extracted and finally, the diagnosis is done based on the extracted features from the pictures. The focus of this study is to develop a robust, unsupervised and sensitive malaria screening technique with low material costs and to lower the human dependency.

Keywords: Malaria, Intensity characteristics, Erythrocyte, Plasmodium, Image Processing, ANN Classifiers