Brain Tumor Segmentation using Multi Level Thresholding using Fuzzy Entropy
A.Nirmala*, Department of Computer Applications, Dr. N. G. P. Arts and Science College, Coimbatore, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 2641-2643 | Volume-8 Issue-5, January 2020. | Retrieval Number: E5944018520/2020©BEIESP | DOI: 10.35940/ijrte.E5944.018520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In image processing field, image processing technique is used to distinguish the object from its image scene at pixel level. The image segmentation process is the significant task in the processing of image field as well as in image analysis. The most difficult task in the image analysis field is the automatic separation of object from its background. To alleviate this problem several image segmentation process is introduced are gray level thresholding, edge detection method, interactive pixel classification method, neural network approach and segmentation based on fuzzy approach This chapter presents the multilevel set thresholding method using partition of fuzzy approach on brain image histogram and theory of entropy. The fuzzy entropy method is applied on multi-level brain tumor MRI image segmentation method. The threshold of brain MR image is obtained by optimized the entropy measure. In this method, Differential Evolution technique is used to find the best solution.
Keywords: Segmentation, Thresholding, Fuzzy Entropy.
Scope of the Article: Fuzzy logics.