Comparison and Denoising of OCT Images with Filters

Telagamalla Gopi

Abstract: Digital image processing involves various algorithms and mathematical operations to analyze or enhance the images. Several types of noises are induced into the images during image transmission or generation. Noises such as gaussian noise, salt & pepper noise, speckle noise and Poisson noise are generally present in most of the images. Different approaches like mean filter, median filter, mode filter, adaptive filter are also available in literature. In this course project, we are trying to analyze the effect of various types of noise on a retinal OCT image by adding different noises to the image and studying which filter is better at reducing different types of noise. Also, we are trying to reduce the noise already present in the OCT image by applying various filters. Quantitative analysis is performed by comparing the PSNR and SNR values.

Keywords: OCT image, Filter, SNR, PSNR, Gaussian noise