[Aggarwal, 2(12): December, 2013] ISSN: 2277-9655 Impact Factor: 1.852 http: // www.ijesrt.com(C)International Journal of Engineering Sciences & Research Technology [3679-3682] IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY A Comparative Study of Various Brain Tumor Detection Algorithms Richa Aggarwal *1 , Amanpreet Kaur 2 *1,2Assistant Professor Department of Information Technology, CEC Landran, Mohalli, Punjab, India Richainfotec23@gmail.com Abstract In recent years, medical image researches for brain tumor detection are attaining more curiosity since the augmented need for efficient and objective evaluation of large amounts of data. Medically, tumors are also known as neoplasms, which are an abnormal mass of tissue resulting from uncontrolled proliferation or division of cells happening in the human body. If such growth is located within the brain, then it is called as brain tumor. Numerous researchers have made the noteworthy survey of the field of medical imaging and soft computing for brain tumor classification. This paper congregates representative works that demonstrate how artificial intelligence (AI) is applied and, which are used frequently to classify the brain tumor images from the normal brain images. Keywords: survey on brain tumor, classification, artificial intelligence, medical imaging Introduction The dawn of medical imaging modalities such as X-ray ultrasound, computed tomography (CT) and magnetic resonance imaging (MRI) has significantly enhanced the diagnosis of human diseases as they offer an efficient means for noninvasively mapping the structure of a subject. Previously, the universal method to investigate imaging data was visual inspection on printed support. Among these for Brain Imaging the MRI (Magnetic Resonance Imaging) is a mainly promising tool due to its soft-tissue contrast and non-invasiveness. MRI exploits radio waves and a burly magnetic field rather than X-rays to offer remarkably clear and exhaustive picture of internal organs and tissues clusters [1]. Brain tumor is any mass that results from an abnormal and an uncontrolled growth of cells in the brain. Its threat level depended on a group of features such as the type of tumor, its location, its size and its state of development [2]. A tumor can cause to injure by rising pressure inside the brain, by shifting the brain or pushing against the skull, and by invading and damaging nerves and healthy brain tissue. The position of a brain tumor influences the type of symptoms that arise. This is because different functions are controlled by different parts of the brain. Brain tumors infrequently spread to other parts of the body outer of the central nervous system (CNS) [3]. Fig1. Sample MRI Brain Images Fig2. Sample CT-Scan Brain Images Image segmentation [4] is the progress of partitioning a digital image into multiple segments (sets of pixels, also known as super pixels). The main objective of segmentation is to simplify and/or modify the representation as an image into something that is more significant and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. Furthermore, image segmentation is the process of assigning a label to each pixel within an image such as that pixels with the same label distribute certain visual characteristics. In case of medical image segmentation the objective is to:  Learn anatomical structure