The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising

The wavelet-domain Hidden Markov Tree Model can properly describe the dependence and correlation of fundus angiographic images’ wavelet coefficients among scales. Based on the construction of the fundus angiographic images Hidden Markov Tree Models and Gaussian Mixture Models, this paper applied exp...

Descripción completa

Detalles Bibliográficos
Autores principales: Cui, Dong, Liu, Minmin, Hu, Lei, Liu, Keju, Guo, Yongxin, Jiao, Qing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Bentham Open 2015
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4645835/
https://www.ncbi.nlm.nih.gov/pubmed/26628926
http://dx.doi.org/10.2174/1874120701509010194
_version_ 1782400875752325120
author Cui, Dong
Liu, Minmin
Hu, Lei
Liu, Keju
Guo, Yongxin
Jiao, Qing
author_facet Cui, Dong
Liu, Minmin
Hu, Lei
Liu, Keju
Guo, Yongxin
Jiao, Qing
author_sort Cui, Dong
collection PubMed
description The wavelet-domain Hidden Markov Tree Model can properly describe the dependence and correlation of fundus angiographic images’ wavelet coefficients among scales. Based on the construction of the fundus angiographic images Hidden Markov Tree Models and Gaussian Mixture Models, this paper applied expectation-maximum algorithm to estimate the wavelet coefficients of original fundus angiographic images and the Bayesian estimation to achieve the goal of fundus angiographic images denoising. As is shown in the experimental result, compared with the other algorithms as mean filter and median filter, this method effectively improved the peak signal to noise ratio of fundus angiographic images after denoising and preserved the details of vascular edge in fundus angiographic images.
format Online
Article
Text
id pubmed-4645835
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Bentham Open
record_format MEDLINE/PubMed
spelling pubmed-46458352015-12-01 The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising Cui, Dong Liu, Minmin Hu, Lei Liu, Keju Guo, Yongxin Jiao, Qing Open Biomed Eng J Article The wavelet-domain Hidden Markov Tree Model can properly describe the dependence and correlation of fundus angiographic images’ wavelet coefficients among scales. Based on the construction of the fundus angiographic images Hidden Markov Tree Models and Gaussian Mixture Models, this paper applied expectation-maximum algorithm to estimate the wavelet coefficients of original fundus angiographic images and the Bayesian estimation to achieve the goal of fundus angiographic images denoising. As is shown in the experimental result, compared with the other algorithms as mean filter and median filter, this method effectively improved the peak signal to noise ratio of fundus angiographic images after denoising and preserved the details of vascular edge in fundus angiographic images. Bentham Open 2015-08-31 /pmc/articles/PMC4645835/ /pubmed/26628926 http://dx.doi.org/10.2174/1874120701509010194 Text en © Cui et al.; Licensee Bentham Open. https://creativecommons.org/licenses/by/4.0/legalcode This is an open access article licensed under the terms of the (https://creativecommons.org/licenses/by/4.0/legalcode), which permits unrestricted, noncommercial use, distribution and reproduction in any medium, provided the work is properly cited.
spellingShingle Article
Cui, Dong
Liu, Minmin
Hu, Lei
Liu, Keju
Guo, Yongxin
Jiao, Qing
The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title_full The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title_fullStr The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title_full_unstemmed The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title_short The Application of Wavelet-Domain Hidden Markov Tree Model in Diabetic Retinal Image Denoising
title_sort application of wavelet-domain hidden markov tree model in diabetic retinal image denoising
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4645835/
https://www.ncbi.nlm.nih.gov/pubmed/26628926
http://dx.doi.org/10.2174/1874120701509010194
work_keys_str_mv AT cuidong theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT liuminmin theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT hulei theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT liukeju theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT guoyongxin theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT jiaoqing theapplicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT cuidong applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT liuminmin applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT hulei applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT liukeju applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT guoyongxin applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising
AT jiaoqing applicationofwaveletdomainhiddenmarkovtreemodelindiabeticretinalimagedenoising

Ejemplares similares