Global and Adaptive Thresholding Technique for White Blood Cell Image Segmentation

Abstract

Global and local thresholding are two thresholding approaches for white blood cell (WBC) image segmentation. Global thresholding determines the threshold value based on the histogram of the overall pixel intensity distribution of the image. In contrast, adaptive thresholding computes the threshold value for each fractional region of the image, so that each fractional region has a different threshold value. In this work, we are assessing both of these approaches for two threshold values. We extended the Otsu’s equation to calculate more than one threshold as it originally designed to find only a single threshold value. Adaptive thresholding first divides an image into fractional-image by considering an imaginary bounding box that surrounds the location of WBC, which involves the Gram-Schmidt orthogonalization method. For segmentation performance evaluation, we compare 35 blood smear test images which segmented by our proposed method, with their corresponding ground truth image to representing them in Zijdenbos Similarity Index (ZSI), precision, and recall measurement. Experimental results show that adaptive thresholding achieves average ZSI, precision and recall, 92.5%, 91.79%, 94.03%, while global thresholding achieves 30.72%, 23.38%, and 99.39% respectively.