ABSTRACT
Image segmentation is an important step in medical image diagnosis system. There are various segmentation methods to partition an image into different subregions on the basis of edge detection, area based or clustering based methods. This paper provides a thorough analysis of different segmentation techniques with morphological operators for brain tumor detection. The different segmentation techniques are k-mean, Entropy filtering, area-based segmentation. After segmenting the image, morphological operators are used to mask the segments. Manual segmentation is used to construct the gold standard for comparing the segmented image. Comparison is performed using performance parameters such as F1 score, Sensitivity, Specificity, Loss Function, precision and Jaccard Coefficient. The elapsed time is also been observed for the segmentation process. The experimental results show that combining segmentation techniques with morphological operation of erosion gives an improved performance over dilation.
