Detection of the Top Anemic Diseases in Blood Smear Images Using Image Quantization Followed by Ensemble of Classifiers

Abstract

Anemia is a condition caused due to the deficiency of Red Blood Cells (RBCs) and hemoglobin in blood. It is an indication to a specific disorder in the human body. Different types of anemic diseases infect the shapes of Red Blood Cells in different ways and the infected cells form various geometric shapes, such as elongated ellipse, triangular shapes, cut circles, boundary interruption in ellipse or circle etc. Leveraging these shapes the type of anemia can easily be identified. We have used various boundary based shape descriptors like shape signatures and color profiles as features for the infected RBCs recognition. The algorithm is followed by preprocessing steps like color channel separation, segmentation through quantization, feature extraction and finally classification of Red Blood Cells and the diseases associated with them. We have achieved 92 % accuracy and the proposed method is cost effective and easy to use.