Today, computer aided system is widely used in various fields. Among them, the brain tumor detection is an important task in medical image processing. Early diagnosis of brain tumors plays an important role in improving treatment possibilities and increases the survival rate of the patients. Manual segmentation of brain tumors for cancer diagnosis, from large amount of Magnetic Resonance Imaging MRI images generated in clinical routine, is a difficult and time consuming task or even generates errors. So, the automatic brain tumor segmentation is needed to segment tumor. The purpose of the thesis is to detect the brain tumor quickly and accurately from the MRI brain image. In the system, the average filter is used to remove noise and make smooth an input MRI image and threshold segmentation is applied to segment tumor region from MRI brain images. Region properties method is used to detect the tumor region exactly. And then, the equation of the tumor region in the system is effectively applied in any shape of the tumor region. Moe Moe Aye | Kyaw Kyaw Lin "Brain Tumor Detection System for MRI Image" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd27864.pdf