Quantitative and Qualitative Measurement of K- Means and Fuzzy C Means, the Detection and Extraction of MRI Cerebellum lesions.
Prathibha G1, H S Mohana2
1Prathibha G, Department of Computer Science & Engineering, N.D.R.K Institute of Technology, Hassan, India.
2Dr. H.S Mohana, Department of Electrical & Instrumentation Engineering, Malnad College of Engineering, Hassan, India.
Manuscript received on 02 August 2019. | Revised Manuscript received on 08 August 2019. | Manuscript published on 30 September 2019. | PP: 6656-6659 | Volume-8 Issue-3 September 2019 | Retrieval Number: C5291098319/2019©BEIESP | DOI: 10.35940/ijrte.C5291.098319
Open Access | Ethics and 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: Clustering is an unaided examination with two totally various procedures: hard clustering and soft clustering. K-Means might be a hard clustering procedure and FCM might be a soft clustering procedure. In this paper, a performance live is administrated on these two algorithms to search out the higher one for detection and extraction of cerebellum lesion in MRI. Each subjective and objective evaluations are administrated. Varied applied mathematical measures like MSE, PSNR, ROI, NROI, Compression ratio, accuracy are utilized for target investigation of the consequences of the near examination of the two calculations. Abstract investigation is administrated by subject specialists. From this examination, it is discovered that FCM is delivering higher quality segmentation results than K-Means regarding accuracy and ROI segregation. Then again, K-Means is overpowering the relatively lesser measure of time for image segmentation than FCM. In this way, on the off chance that accuracy is given parcel of need than time complexness, at that point FCM should be an essential inclination.
Keywords: Cerebellum lesion, K means clustering, Fuzzy C Means, Performance measurements.
Scope of the Article: High Performance Computing