Fully Automated Detection and Classification of White Blood Cells

The measure of White Blood Cells (WBC) in the blood is an important indicator of pathological conditions. Computer vision based methods for differential counting of WBC are increasing due to their advantages over traditional methods. However, most of these methods are proposed for single WBC images which are pre-processed, and do not generalize for raw microscopic images with multiple WBC. Moreover, they do not have the capability to detect the absence of WBC in the images. This paper proposes an image processing algorithm based on K-Means clustering to detect the presence of WBC in raw microscopic images and to localize them, and a VGG-16 classifier to classify those cells with a classification accuracy of 95.89%.