• Sneha
• Priyanka

For the MRI image segmentation and classification, several automatic algorithms are present still it is required to build up an efficient algorithm. From MRI images tumor area can be detected, segmented and extracted accurately by the doctors only through their experience. This paper introduces a new technique to detect the tumor using SVM and morphological operations. By providing better accuracy in output the limitations and complexities are reduced. This paper presents SVM algorithm which is used to segment the tumor and obtained the parameters like MSE (mean square error), accuracy and PSNR (peak signal to noise ratio). After the removal of noise SVM classifier is used to segment the image afterward morphological operations are applied to extract the tumor from segmented region. The proposed SVM classifier provides 97.87% accuracy. Proposed work is also compared with existing algorithms.

Brain tumor segmentation, MRI, support vector machine (SVM) classifier, morphological operations.

"Brain tumor detection using morphological operations and SVM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.866-869, June 2019, Available :http://www.jetir.org/papers/JETIR1906G32.pdf

"Brain tumor detection using morphological operations and SVM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp866-869, June 2019, Available at : http://www.jetir.org/papers/JETIR1906G32.pdf