Avanaki, Mohammad R. N. and Laissue, Philippe and Podoleanu, Adrian G.H. and Hojjatoleslami, Ali (2008) Denoising Based on Noise Parameter Estimation in Speckled OCT Images Using Neural Network. In: Podoleanu, Adrian G.H., ed. 1st Canterbury Workshop on Optical Coherence Tomography and Adaptive Optics. Proceedings of SPIE . SPIE, Bellingham, Washington. ISBN 978-0-8194-7380-6. (doi:10.1117/12.814937) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:22678)
The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. | |
Official URL: http://dx.doi.org/10.1117/12.814937 |
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.
Item Type: | Book section |
---|---|
DOI/Identification number: | 10.1117/12.814937 |
Uncontrolled keywords: | Optical Coherence Tomography (OCT), Neural Network, Speckle Noise Reduction, No-Reference (NR) metrics |
Subjects: |
Q Science T Technology R Medicine |
Divisions: |
Divisions > Division of Natural Sciences > Biosciences Divisions > Division of Natural Sciences > Physics and Astronomy |
Depositing User: | S.A. Hojjatoleslami |
Date Deposited: | 01 Oct 2009 07:47 UTC |
Last Modified: | 05 Nov 2024 10:01 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/22678 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):