Development of automatic identification and classification system for malaria parasite in thin blood smears based on morphological techniques

This paper investigates the possibility of rapid and accurate automated diagnosis of red blood cell disorders and describes a method to detect and classify malarial parasites in blood sample images acquired from light microscopes. Malaria is an infectious disease and is mainly diagnosed by microscopical evaluation of Giemsa stained blood smears. Since it causes a serious health problem, automation of the evaluation process is of high importance. The image classification system is designed to positively identify malaria parasite in thin blood smears. Morphological and novel threshold selection techniques are used to identify red blood cell and possible parasites present on microscopic slides. Image features based on colour, texture and the geometry of the cells and parasites are generated. Classifier based on back propagation feed forward neural network distinguishes between parasite infected and non-infected blood images.