期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：1
页码：1039
DOI：10.15680/IJIRSET.2016.0501056
出版社：S&S Publications
摘要：Image Segmentation is the process of partitioning a digital image into non-overlapping distinct regions,so that significant information about the image could be recovered and various analysis could be performed on thatsegmented image. In this paper, we present an efficient brain tumor segmentation methods, that can detect tumor andlocate it in the brain MRI images. The method uses computer aided method for segmentation (detection) of brain tumorbased on the three segmentation methods namely K-means clustering, fuzzy C-means clustering, thresholding withmorphological operations. K-Means clustering and fuzzy C-means clustering techniques are used for the purpose ofsegmentation of brain tissue classes which is considered efficient and effective for the segmentation of an image. Andthresholding with morphological operations method allows the segmentation (detection) of tumor tissue with high levelaccuracy and reproducibility comparable to clustering segmentation methods. At the end of the process the tumor isextracted from the MR image, its exact position and some features also determined. It is observed that the experimentalresults of the thresholding with morphological operations is a very promising in the field of brain tumor segmentationcompare with clustering methods.
