An improved methodology for blood cell counting

In this paper, we present an approach for counting blood cells during blood smear test. The approach presented in this paper eliminates the major problem of overlapping cells while counting by segmentation using morphological watershed transformation and regional maxima computation providing high degree of accuracy. Simulation results of counting red blood cells (RBCs), white blood cells (WBCs) and platelets in blood smear test images are also presented. The simulations are done in MATLAB®.