Share Email Print
cover

Proceedings Paper

Denoising based on noise parameter estimation in speckled OCT images using neural network
Author(s): Mohammad R-N. Avanaki; Philippe P. Laissue; Adrian G. Podoleanu; Ali Hojjat
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a neural network based technique to denoise speckled images in optical coherence tomography (OCT). Speckle noise is modeled as Rayleigh distribution, and the neural network estimates the noise parameter, sigma. Twenty features from each image are used as input for training the neural network, and the sigma value is the single output of the network. The certainty of the trained network was more than 91 percent. The promising image results were assessed with three No-Reference metrics, with the Signal-to-Noise ratio of the denoised image being considerably increased.

Paper Details

Date Published: 30 December 2008
PDF: 9 pages
Proc. SPIE 7139, 1st Canterbury Workshop on Optical Coherence Tomography and Adaptive Optics, 71390E (30 December 2008); doi: 10.1117/12.814937
Show Author Affiliations
Mohammad R-N. Avanaki, Univ. of Kent (United Kingdom)
Philippe P. Laissue, Univ. of Kent (United Kingdom)
Adrian G. Podoleanu, Univ. of Kent (United Kingdom)
Ali Hojjat, Univ. of Kent (United Kingdom)


Published in SPIE Proceedings Vol. 7139:
1st Canterbury Workshop on Optical Coherence Tomography and Adaptive Optics
Adrian Podoleanu, Editor(s)

© SPIE. Terms of Use
Back to Top