Red blood cell counting is difficult to perform by automated visual inspection because of the large number of connected RBCs in blood smear slides. This paper presents anew algorithm to segment connected RBCs in blood smear images based on the distance per displacement ratio criterion. First, RBCs were separated from white blood cells and platelets by performing thresholding on the b* component in Lab color space. Next, connected RBCs and single RBCs were separated by using the Circular Compactness Shape Factor criterion. Later, points on boundaries of connected RBCs with high curvature were marked as concave points. Each concave point was then paired to a nearby concave point that maximizes the distance per displacement ratio criterion. Finally, a set of paired concave points was used as information for segmenting connected RBCs. Experimental results of RBC counting, including connected and single RBCs, on 50 blood smear images, revealed that the proposed algorithm can achieve an average accuracy of up to 99.22% Article DOI: https://dx.doi.org/10.20319/mijst.2016.s11.132143 This work is licensed under the Creative Commons Attribution-Non-commercial 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
SEGMENTATION OF CONNECTED RED BLOOD CELLS BASED ON DISTANCE PER DISPLACEMENT RATIO MAXIMIZATION CRITERION
2015-07-01
doi:10.20319/mijst.2016.s11.132143
MATTER: International Journal of Science and Technology; Vol 1 No 1 (2015): Special Issue; 132-143 ; 2454-5880
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Maximization of Thrust-Torque Ratio of a Coaxial Rotor
AIAA | 2005
|Parametric model-based motion segmentation using surface selection criterion
British Library Online Contents | 2006
|Vectorial scale-based fuzzy-connected image segmentation
British Library Online Contents | 2006
|