Novel and Efficient Approach for Automated Separation, Segmentation, and Detection of Overlapped Elliptical Red Blood Cells

Abstract

Shape recognition is considered as one of the challenges in automated digital image analysis and computer vision. One of the most commonly used shapes is the ellipse which is of great importance for many industrial and biomedical applications. In this study, a novel technique is proposed for segmenting and separating of overlapped elliptical shape objects using concavity analysis and several morphological image processing techniques. A comparative study of the detection speed and accuracy of elliptical objects between Iterative Random Hough Transformation (IRHT) algorithm approach and Direct Least Squares Fitting (DLSF) of Ellipses method has shown the great superiority of DLSF in both the speed and accuracy of recognition. The validation of the proposed techniques for segmentation and detection along with calculation of the efficiency of the system has shown those techniques to be robust and effective for automation of synthetic and real elliptical shapes. The red blood cells (RBCs) microscopic images of the blood smear in Hereditary Elliptocytosis disorder is studied as real elliptical shapes and a quantitative analysis was implemented on the detected RBCs, where the distribution parameters of the ellipse size (area), Roundness, Eccentricity, and Ellipticity are estimated in addition to RBCs counting. The proposed detection approach is successful in building a fully autonomous and accurate system with ellipse analysis capabilities.