Malaria Detection Using Machine Learning (K-NN)

to detect the presence of Malaria parasites in Human Blood Cells and to determine how much it is affected. We have developed a machine learning method that can detect malaria parasites in thick blood smear images. Our method consists of two processing steps. To start with, we apply a force based Iterative Global Minimum Screening (IGMS), which plays out a quick screening of a thick smear picture to discover parasite up-and-comers. Then, a customized K-Nearest Neighbor (K-NN) classifies each candidate as either parasite or background. Malaria - a parasitic disease health problem which leads to millions of deaths especially in remote villages. This disease arises due to damaging of red blood cells. This paper presents a survey on detection / prediction of malaria disease using various machine learning techniques, Image Processing techniques and various clinical methods like rapid test, Nested PCR etc. In our observation, we found that machine learning techniques have wider applicability for critical diagnosis of malaria which in turn helps the clinicians for diagnosing the disease.