Power Law Enhancement Based Fuzzy C-Means Retinal Blood Vessel Segmentation
Sekar Mohan1, Vijayarajan R2
1Sekar Mohan, Department of Mechanical Engineering, AAA College of Engineering and Technology, Sivakasi (Tamil Nadu), India.
2Vijayarajan R, Department of Electronics & Communication Engineering, RGM College of Engineering & Technology, Nandayal (Andhra Pradesh), India.
Manuscript received on 26 February 2019 | Revised Manuscript received on 13 March 2019 | Manuscript Published on 17 March 2019 | PP: 54-58 | Volume-7 Issue-ICETESM18, March 2019 | Retrieval Number: ICETESM14|19©BEIESP
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: The detection and analysis of retinal blood vessels is vital for the diagnosis and treatment of retinal diseases. Characteristics such as vessel lengths, diameters, bifurcations, tortuosity and reflectivity are the key to analyze retinal blood vessels for hypertension, diabetic retinopathy and macular degeneration. This manuscript proposes a power law enhanced Fuzzy C-Means method for retinal blood vessel segmentation. Morphological operations are also used to get proper vessel structure and to eliminate unwanted regions. The proposed methodology is experimented for various values of gamma and the appropriate value is suggested for power law enhancement of retinal images. For performance evaluation, normal retinal images from STARE database are tested and the results are compared with other methods experimented on the same database. It is observed from the metrics that the proposed methodology is able to achieve average accuracy of 98.45%.
Keywords: Fuzzy C-Means, Morphological Operations, Power Law Enhancement, Retinal Vessel Segmentation, Retinopathy.
Scope of the Article: Fuzzy Logics