Open AccessBrain Tumor Segmentation using FCM and Symbolic Feature
Author(s) -
S. Manjunath,
Deepak Athipan A M B,
Dr Raveesh B N
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1130.0886s19
Subject(s) - artificial intelligence , brain tumor , segmentation , pattern recognition (psychology) , feature (linguistics) , computer science , fuzzy logic , image segmentation , image (mathematics) , computer vision , pathology , medicine , linguistics , philosophy
The brain tumor segmentation from image is interesting and challenging in the field of image processing and pattern recognition. An early detection of a brain tumor region helps the patient to take the correct medicine and increase the rate of the survival.The brain tumor segmentation is a process of differentiating the abnormal tissues and normal tissues. most common types of brain tumors are Benign and Malignant tumors. In this paper, the Fuzzy C-Means (FCM) approach is used to cluster the abnormal cells region and normal cells region in the brain image. The possible noises are removed by employing the median filter and morphological function is applied to extract the possible tumor region. The true tumor region is extracted with the help of symbolic features. Finally, the proposed methods is tested on T2- weighted MR brain images