Segmentation of Brain Tissues from MRI using Bilateral Filter Based Fuzzy C-Means Clustering
Jaspreet Kaur1, Chandan Singh2
1Jaspreet Kaur, Department of Computer Science and Application, Punjab University, Chandigarh, India.
2Dr. Chandan Singh, P.H.D. Department of Applied Mathematics, Indian Institute of Technology, Kanpur, India.
Manuscript received on 20 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 26 August 2019 | PP: 249-255 | Volume-8 Issue-9S August 2019 | Retrieval Number: I10390789S19/19©BEIESP | DOI: 10.35940/ijitee.I1039.0789S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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: This paper represents a segmentation method that incorporates both local spatial information and intensity information in an efficient fuzzy way. The newly introduced segmentation method BWFCM is an abbreviation of Bilateral weighted fuzzy C-Means. BWFCM uses the advantage of the bilateral filter in its objective function as a bilateral kernel that replaced the spatial neighborhood term with Gaussian weighted Euclidean distance mean of the intensity value of neighbor pixels. BWFCM preserves the damping extent of adjacent pixels while removing the noise because of its averaging behavior. The BWFCM segmentation method is perceived to be very focused on several state-of-the-art methods on a range of images. Experiment analysis on simulated and real MR images show that the proposed method BWFCM provides superior performance over the conventional FCM method and several FCM based methods. The proposed method BWFCM has weakened the impact of Rician noise and other artifact and gives more accurate and efficient segmentation results.
Keywords: Fuzzy Clustering, Intensity information, MRI segmentation, Noise, Spatial information.
Scope of the Article: Fuzzy Logics