Automated blood cells segmentation and counting

Abstract

Blood cell segmentation and identification are centered on the pre-processing of the image, segmentation of the Regions of Interest (ROI) and identification or classification of the cells. Recent studies have suggested different method for segmentation and identification of blood cells. Counting of blood cells (rbc or wbc) in blood cell images is very important to detect as well as to follow the process of treatment of many diseases like anaemia, leukaemia, lung nodule etc. However, locating, identifying and counting of blood cells manually are tedious and time consuming that could be simplified by means of automatic analysis, in which segmentation is a crucial step. We present an approach to automatic segmentation and counting of blood cells in microscopic blood cell images using Hough Transform. Morphological is a very powerful tool in image processing, and it is been used to segment and extract the blood cells (rbc or wbc) from the background and other cells. The algorithm used features such as shape of desired blood cells for counting process. The result presented here is based on images with normal blood cells. The process is initiated by image acquisition and image enhancement process. Noise removal from the blood smear image is the first step. This removes the unwanted pixels from the image. Further the edges are preserved and binarization of the image is performed, separating the region of interest from the background. Further the edges are preserved and binarization of the image is performed. Then the task is to differentiate red blood cells from the various other components in the blood by the segmentation process. Morphological operations are applied on the blood image followed by RBC counting using Hough transform which is an efficient image segmentation technique. The primary goal of the proposed system is to detect and count all the RBC including the overlapping ones in the blood smear image.