Abstract

In biomedical, tumor detection and removal is one of the major medical issue. Brain tumor is a disease of the brain where cancer cells arise in the brain tissue to form a mass of cancer tissue that interferes with brain functions such as manage muscle, sense, memory and other body functions. Tumors composed of cancerous cells are called Malignant tumors and those composed of non-cancerous cells are called Benign tumors. There are so many ways to diagnose tumor in brain include Neurologic exam, MRI, CT scan, Angiogram, Spinal tap and Biopsy. Medical imaging has tremendous advantage in diagnosis of the disease where Magnetic Resonance Imaging plays an important role. This paper aims to enhance the accuracy level in the detection of brain tumor and provides better performance than existing method based on high accuracy rate and low computing time. The process of tumor detection comprises three steps (i) Segmentation (ii) Feature extraction (iii) Classification. Various algorithms are developed for image processing in which we take Histogram thresholding for image segmentation and Support Vector Machine (SVM) for classify the image as Benign or Malignant.