Colour image segmentation of malaria parasites in thin blood smears using C-Y colour model and K-Means clustering

Abstract

Malaria is a life threatening disease that is responsible for nearly one million deaths each year. With the large number of cases diagnosed over the year, rapid detection and accurate diagnosis which facilitates prompt treatment is an essential requirement to control malaria. Due to the requirement for rapid detection of malaria, the current study has proposed the colour image segmentation of malaria parasites that has been applied on malaria images of P. vivax species. Here, the proposed method provides a basic step for detection of the presence of malaria parasites in thin blood smears. In order to obtain the segmented parasite, the malaria image will first be enhanced using global contrast stretching. Then, an unsupervised segmentation technique namely k-means clustering algorithm is used to segment the parasite from its complicated blood cells background. Here, the five colour components of C-Y colour model which are R-Y, B-Y, luminance, hue and saturation components are analyzed to identify the colour component that perform significant segmentation performance. Finally, median filter and seeded region growing area extraction algorithms have been applied in order to smooth the image and remove any unwanted regions from the image, respectively. The proposed segmentation method has been analyzed using 50 malaria images of gametocyte stage. Overall, the results indicate that k-means clustering using saturation component of C-Y colour model has produced the best segmentation performance with segmentation accuracy of 99.19%.