Automatic Brain Tumour Diagnosis and Segmentation: based on SVM Algorithm
Ahsanullah Umary1, Harpreet Kaur2
1Ahsanullah Umary*, Student, M.E (ECE) at Chandigarh University, Mohali, India.
2Harpreet Kaur, Assistant Professor in Department of Computer Science at Chandigarh University, Mohali, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 31, 2020. | Manuscript published on April 10, 2020. | PP: 1079-1084 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4190049620/2020©BEIESP | DOI: 10.35940/ijitee.F4190.049620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Brain tumour is undesirable expansion of destructive cell in or around the cranium. It can directly attack our healthy brain cell within the skull or it might invasion indirectly from disparate organs of the body such as lung cancer, breast lump. Its size becomes double within 25-30 days. Brain tumour is one of the highest threatening illnesses among cancerous diseases. Unfortunately possibility of death patients from brain tumour is to a greater extent in contrast with other illness. If we didn’t treat the cerebrum tumour at near the beginning the possibility of patient death will be very high in just one half year. Hence it’s very important for the research to find away to automatically recognize brain tumour and classify it to cancerous and non-cancerous tumor. That’s why these day’s one of the most widely research zone in image processing is brain tumor recognition and categorization. This article present various phase involves in brain cancer recognition and categorization such as pre-processing, cleavage, characteristics extraction, and classification of brain tumour by utilizing SVM algorithm .The proposed system execution and analysis was examined which achieved favorable outcome, high accuracy at minimal time in contrast weigh the research completed previously.
Keywords: Peak Signal to Noise Ratio (PSNR), Support Vector Machine (SVM), Grey- Level Co-Occurrence Matrix (GLCM), Mean Square Error (MSE), Graphical User Interface (GUI).
Scope of the Article: Signal and Image Processing