A comparative study of otsu and entropy based segmentation approaches for tumour extraction from MRI

Brain tumour has become a precarious issue in European continents. It can be easily cured if diagnosed and treated at very early stages. In this article we have focused our research on the lesion extraction from tumour sample using entropy-based approaches from MRI scans of infected cases. Various ideal and general entropy functions viz; Havrda, Shannon, Renyi, Kapur, Vajda respectively are investigated for the evaluation of randomness measure at each possible threshold in gray range. The results retrieved shows an outperforming behaviour of general entropy measure of Havrda function as compared to any other existing entropy functions.