Segmentation of magnetic resonance images of brain using thresholding techniques

• Published in: ISPCC 2017 : 4th IEEE International Conference on Signal Processing, Computing and Control : September 21-23, 2017 pp. 311 - 315
• Main Authors: Dogra, Jyotsna, Sood, Meenakshi, Jain, Shruti, Parashar, Navdeep
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2017
• Subjects: Fuzzy C-Mean Clustering; Graph-Cut; High definition video; K-mean clustering; Segmentation; Split and merge; Threshold
• DOI: 10.1109/ISPCC.2017.8269695

In the recent years, image segmentation has become one of the important technique in several general-purpose fields where it has been used to extract region of interest from the background. Image segmentation is a classic subject in the field of image processing which has a special focus on image processing techniques. Since, in literature there is no general solution to the image segmentation problem, various techniques have been employed to effectively solve these problems combined with the domain knowledge. A lot of brainstorming has been done to come up with an optimal technique to make images smooth and easy to evaluate. Among various image segmentation techniques, thresholding is one of the simplest techniques that has been used for image segmentation where the region of interest has been extracted from the background by comparing the pixel values with the threshold value. To obtain the threshold value histogram of the image has been calculated. The results shows that any abnormality can be localized easily in horizontal divided MRI brain image rather than in vertical divided MRI image.