An efficient brain tumor detection from MRI images using entropy measures

MRI-a computer based image processing technique for detecting and diagnosing brain tumor. Segmentation of images in MRI helps us to detect - tumor size, location and shape. There are many techniques of segmentation in image processing. Segmentation techniques are region based, boundary based and threshold based. Threshold technique involves an entropy based algorithmic techniques that are highly useful for early detection of brain tumor. In this paper, we are comparing and analyzing various threshold-entropy based segmentation methods on the basis of simulation results. Entropy methods like shannon, Renvi, Vajda, Havrda-Charvat and Kapur are applied to the MRI images of brain tumor or any internal structure of our body, are analyzed and compared An approach of threshold selection of images based on entropy methods are found highly effective in diagnosis of brain tumor. After comparing and analyzing through simulation results, we observed that havrda-charvat entropy performs better than any other entropy algorithms.