Automatic White Blood Cell Counting Approach Based on Flower Pollination Optimization Multilevel Thresholoding Algorithm

Abstract

This paper presents an swarm optimization approach based on flower pollination optimization algorithm for multilevel thresholding by the criteria of Otsu minimizes the weighted within-class variance to make the optimal thresholding more effective. An application of microscopic white blood cell imaging has been chosen and the proposed approach has been applied to see their ability and accuracy to segment and count the blood cells. An adaptive watershed segmentation algorithm was applied that depends on a mask created from the required microscopic image to detect the minima points for segmenting the overlapped cells. The cell counting process depends on labeling the connected regions of the segmented binary image and count the labeled cells. The proposed approach archives promised results with respect to quality measures of accuracy, peak to signal-to-noise ratio (PSNR) and the root mean square error (RMSE) on microscopic images. Experimental results are recorded for the proposed approach over ten selected different images with accuracy of 98.4% that present better accuracy over the manual traditional techniques.