Brain Tumor Detection Using Modified Histogram Thresholding-Quadrant Approach
K. Nithya, Mri Image · 2012
In medical image processing brain tumor detection is one of the challenging task, since brain images are complicated and tumors can be analyzed only by expert physicians. So In this paper brain tumor is detected at various levels. First the pre-processing is done by median filter in order to reduce noise and then edge detection is done by using canny filter, then Segmentation is done by means of histogram clustering in which the tumor affected image is divided into quadrants and threshold value is set , based on this value tumor is detected. Secondly the other technique involved is superimposing of the tumor affected with the healthy image. This method does not require any initialization while the others require an initialization inside the tumor. The third method in which, the histogram is calculated and the threshold is fixed. This work is carried in MRI image. The experimental results illustrate the usefulness of the new method.