OCT image Denoising Based On K-SVD Method

Journal Title: GRD Journal for Engineering - Year 2016, Vol 1, Issue 0

Abstract

Enhancement of the images will be more helpful in surveillances and remote sensing applications. While increasing the size of the image the original image quality will be affected. In order to avoid the loss of quality while enhancing the image, Non Local Means (NLM) Optimized Sparse Method is used. The noises and the pixel differences occurring in the up sampling and down sampling of the images were identified and they were removed based on the proposed method. Finally the images were enhanced by the edge enhancement process. The performance of the proposed method is proved using the performance parameters. The input OCT images were taken as input. Noises were added to the input images producing a noisy images. The input images were denoised based on the K-SVD process. K-SVD is a generalization of the k-means clustering method, and it works by iteratively alternating between sparse coding the input data based on the current dictionary, and updating the atoms in the dictionary to better fit the data. It aims to partition n observations into few clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. The denoised images were then clustered and edges of the clusters were identified. The clusters were estimated based on the FCM clustering process. The performance of the process is then measured using the performance parameters like PSNR, MSE and SSIM.

Authors and Affiliations

A. Priyanga, V. Nandhini Devi, M. Tamilarasi, Dr. S. Venkatanarayanan

Keywords

Related Articles

Design, Analysis and Optimization of Non Standard Weld Neck Body Flange in Small Pressure Vessel

Pressure vessels are leak proof containers, as the name implies, their main purpose is to contain a given medium under pressure and temperature. Pressure vessels are commonly used in industry to carry both liquid and gas...

Implementation of Fault Tolerant FIR Filter for Digital Communication Systems

A realistic communication system is not free from noise. So the transmission of information through may rather be corrupted by noise in the channel. Therefore it is necessary for every communication systems to have suita...

Removal of Hexavalent Chromium from Wastewater by Adsorption: A Review

Amount of waste water containing heavy metals is increasing in the environment due to industrialization. Heavy metals treatment of waste water should be done due to increase in pollution and scarcity of water. Hexavalent...

Automated Solar Panel Tracking Cum Cleaning System

Accumulation of dust on the surface of the solar panels is a natural phenomenon. These accumulated dust particles act as an obstrucle and obstruct the rays from reaching the panel. These particles act as external resista...

Experimental Investigation of TIG Welding for Stainless Steel using Design of Experiment

Gas tungsten arc welding is a fusion welding process having broad application in industry. In this experiment selected three process parameters like current, groove angle and welding speed and range was decide for each p...

Download PDF file
  • EP ID EP303146
  • DOI -
  • Views 106
  • Downloads 0

How To Cite

A. Priyanga, V. Nandhini Devi, M. Tamilarasi, Dr. S. Venkatanarayanan (2016). OCT image Denoising Based On K-SVD Method. GRD Journal for Engineering, 1(0), 553-558. https://europub.co.uk/articles/-A-303146