Classifying white blood cells from a peripheral blood smear image using a histogram of oriented gradient feature of nuclei shapes

Abstract

Researchers developed various methods and algorithms to classify white blood cells (WBCs) from blood smear imagesto assist hematologistsand to developan automatic system. Furthermore, the pathological and hematological conditions of WBCsare related to diseases that can be analyzed accurately in a shorttime. In this work, we proposed a simple technique for WBC classification from a peripheral blood smear image based on the types of cell nuclei. The developed algorithms utilized a histogram of oriented gradient(HOG)feature typically known for application inhumandiseasedetection. The segmentation of WBC nuclei utilizes a YCbCr color space and K-means clustering techniques. The HOG feature contains information aboutthe cell nucleishapes, which then is classified using asupport vector machine (SVM) and backpropagation artificial neural network (ANN). The results showthat the proposed HOG feature is useful for WBC classification based on the shapesof nuclei. We are able to categorize the type of a WBC based on itsnucleusshape with more than 95% accuracy.

Keywords

• histogram of oriented gradient
• k-means clustering
• ycbcr color space
• wbc classification
• microscopic blood smear image