OVERLAPPING SICKLE CELLS DETECTION AND SEPARATION USING MARKERBASED WATERSHED SEGMENTATION

Abstract

Sickle cells are abnormalities of the Red Blood Cells (RBCs). The focus of this research work is to detect sickle cells, normal RBCs, and to separate the overlapping cells present in a blood film image and also to identify the percentage of each detected cells. The image processing techniques used for the detection of these RBCs consist of five main steps which are, image acquisition and reading, image preprocessing, feature extraction, RBCs classification, and final result. The Marker-Based Watershed Segmentation (MBWS) method was used to separate the detected overlapping cells. To test the accuracy of this system, the system's result was compared to the result of the traditional method of detection and count of RBCs used in the hospital. The identification and separation of the overlapping cells performed by the proposed system made the system provide more accurate result as compared to the traditional method. The limitations encountered by the system includes, inadequate separation of the overlapping cells due to the under segmentation problem of the technique (Marker-Based Watershed Segmentation) used, the quality of images used, and also the cells at the boundary were eliminated together with its diagnostic features which it may possess