SLIC Segmentation for Tumor Detection & Classification using SVM
Pooja Shah1, Rajkumar S2
1Pooja Shah, Computer Science Engineering & Technology, VIT Vellore (Tamil Nadu), India.
2Rajkumar S, Computer Science Engineering & Technology, VIT Vellore (Tamil Nadu), India.
Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 377-381 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6157048419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Uncontrolled growth of cells in brain is termed as brain tumor. Tumor almost gets double within 25 days. If it is not detected at early stage, it may lead to death nearly in six months. Human inspection through MRI or CT scan images are time consuming. Scanning large number of images by human is time taking and result may not always be correct. For this reason, an automated tumor detection process is required which helps scanning image faster and model which give correct results always. Our proposed system aims for differentiate between the MRI images with non-tumor or tumor. By using the super pixel segmentation, it will detect the tumor region and further with the SVM classifier it will classify the type or tumor (e.g.: pituitary tumor, meningioma or glioma). Proposed model identifies tumor more accurately with the accuracy of 87% compared to current traditional method.
Keywords: Support Vector Machine, Super pixels, Median Filtering, SLIC
Scope of the Article: Machine Design