Improved Method of OCT Image Segmentation for the Detection and Classification of Retinopathy Diseases
Saya Nandini Devi M1, Santhi S2
1Saya Nandini Devi M*, Research Scholar, Department of Electronics and Instrumentation Engineering, Annamalai University, Chidambaram, India,
2Santhi S, Department of Electronics and Instrumentation Engineering, Annamalai University, Chidambaram, India.

Manuscript received on November 12, 2019. | Revised Manuscript received on November 23, 2019. | Manuscript published on 30 November, 2019. | PP: 8747-8753 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9146118419/2019©BEIESP | DOI: 10.35940/ijrte.D9146.118419

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 (

Abstract: Image Segmentation is the process of dividing an image into regions or objects for the purpose of extracting useful information. It plays vital and dominant role in medical image analysis. OCT is a high speed and non-invasive method to determine three dimensional images of retina. This paper presents an improved method of automated OCT image segmentation in order to detect and classify Retinopathy diseases. Discrete wavelet transform (DWT) is a multiresolution approach and is widely used for OCT image segmentation. K-Means Cluster (KMC) approach is popular among researchers that offers better results for extracting the features for image segmentation. This work compares the segmentation process based on DWT with KMC and presents a better segmentation method comprising of K-Means Cluster with Genetic Algorithm Optimization (KMC-GAO) that identifies cluster centroid for obtaining the improved image segmentation performance of an OCT image. The performance metrics such as Structural Content (SC), Rand Index (RI), Variation of Information (VOI) and Global Consistency Error (GCE) are evaluated for all these segmentation techniques and it is observed that KMC-GAO segmentation offers better result than DWT method and KMC approach.
Keywords: Discrete Wavelet Transform, K-Means Cluster, Genetic Algorithm, Image Segmentation..
Scope of the Article: Classification.