An Automated Dual Threshold Band-Based Approach for Malaria Parasite Segmentation from Thick Blood Smear

Thick blood smear examination essentially plays an important role in rapid screening of malaria parasite. In this paper, an automatic malaria parasite detector is proposed to perceive the malaria-infected blood cells in a stained thick blood smear image. The detector hence can verify presence of malarial parasites in blood cells and count the number against each white blood corpuscle. It could precisely accelerate the process of diagnosing malaria in human blood and thus reduces the chances of human errors. Here, an automated image segmentation technique has been developed that proposes to efficiently improve the accuracy over manual techniques. The experimental results show that the proposed method can provide impressive performance in segmenting the malarial parasites from a thick blood smear image on some published malaria dataset and also taken under an origami-based paper microscope. The algorithm makes use of certain preprocessing methods for comparatively better results in the proposed intensity-based segmentation technique, followed by a dual threshold band-based technique. The experimental results are comparable to other existing and traditional malaria segmentation processes.