This paper describes the efficient framework for the extraction of brain tumor from the MR images. Before the segmentaion process, median filter is used to filter the image, Then, morpholigical gardient is computed and added with the filtered image for the intensity enhancement. After the enhancement process, the thresholding value is calculated using the mean and standard deviation of the image. This threholding value is used to binarize the the image followed by the morphological opreations. Moreover, the combination of the morphological operations allows to compute local thresholding image supproted by flood-fill algorithm and pixel replacement process finally to extract the tumor from the brain. Thus, it provides a new source of evidence in the field of segmentation that the specialist can aggregate with the segmenation results to soften it is own decision.
展开▼