Comparative Study on Different Local Adaptive Thresholding Techniques for Detection of Sickle Cell Anaemia from Microscopic Blood Images

Modern image processing techniques are playing an important role in the detection and diagnosis of several medical abnormalities nowadays. In the process of analysis of any image, thresholding is a significant stage. Various researchers have developed different tools for image thresholding depending on the type of applications. Adaptive thresholding is a powerful tool in processing medical images for diagnosis of various diseases. In this work several adaptive image thresholding techniques are being used in processing the blood images of patients suffering from Sickle Cell Disease (SCD). The Sickle cell anaemia is a disorder of inherited type where defective haemoglobin distorts the shape of the red blood cell. It is essential to accurately identify the distorted red blood cells (RBCs) for faster diagnosis of this disease. Although different adaptive thresholding techniques like Niblack, Bernsen, Sauvola and NICK have extensively been used for segmentation purpose, this paper focuses mainly on applying these tools for image thresholding for detection of Sickle cell anaemia from microscopic blood images and providing a comparative analysis.