Classification of Red Blood Cell using Texture Analysis

Red blood cell count plays a vital role in medical diagnosis. If the numbers of red blood cells are less or more in count, it could lead to several diseases. There are several methods to count red blood cells that involve conventional as well as automatic methods. Conventional methods require high skills and experience pathologist to determine the shape and count of red blood cells. This method involves manually counting the number of cells under a microscope that is conducted by a pathologist that usually generates inaccurate results. There are also some automatic methods present that are basically the hardware solutions such as ‘Automated Haematology Counter’ but developing countries such as India are not capable of installing such expensive machines in every hospital laboratory. As a solution, in this project an automated RBC counting and classification system is proposed to speed up the time consumption and to reduce the potential wrongful identification RBC. This paper presents the preliminary study of automatic blood cell counting based on digital image processing. The number of blood cell count the may be use to diagnose the patient as well as detection of important oncogenic patterns.