Study of the Noise Level in the Colour Fundus Images

Toufique Soomro; Junbin Gao

doi:10.1007/978-3-319-24474-7_22

Study of the Noise Level in the Colour Fundus Images

Toufique Soomro, Junbin Gao

Research output: Book chapter/Published conference paper › Conference paper › peer-review

3 Citations (Scopus)

Abstract

Diabetic Retinopathy (DR) causes vision loss insufficiency due to impediment rising from high sugar level conditions disturbing the retina. The Progression of DR occurs in the Foveal avascular zone (FAZ) due to loss of tiny blood vessels of capillary network. Due to image acquisition process of fundus camera, the colour retinal fundus image suffers from varying contrast and noise problems. To overcome varying contrast and noise problem in fundus image, the technique has been implemented. The technique is contained on the Retinex algorithm along with stationary wavelet transform. The technique has been applied on 36 high resolution fundus (HRF) image database contain the 18 bad quality images and 18 good quality images. The RETSWT (RETinex and Stationary Wavelet Transform) developed with introduces denoising techniques. Stationary wavelet transform is used as denoised technique. RETSWT achieved the average PSNR improvement of 2.39 db good quality images else it achieved the average PSNR improvement of 2.20 db in the bad quality images. The RETSWT image enhancement method potentially reduces the need of the invasive fluorescein angiogram in DR assessment

Original language	English
Title of host publication	ICDS 2015
Publisher	Springer-Verlag London Ltd.
Pages	159-168
Number of pages	10
Volume	9208
DOIs	https://doi.org/10.1007/978-3-319-24474-7_22
Publication status	Published - 2015
Event	International Conference on Data Science - University of Technology Sydney , Sydney, Australia Duration: 08 Aug 2015 → 09 Aug 2015 https://link.springer.com/book/10.1007/978-3-319-24474-7 (Conference proceedings)

Conference

Conference	International Conference on Data Science
Country/Territory	Australia
City	Sydney
Period	08/08/15 → 09/08/15
Internet address	https://link.springer.com/book/10.1007/978-3-319-24474-7 (Conference proceedings)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-24474-7_22

Cite this

@inproceedings{992bc5be03214f35b899d039c9345823,

title = "Study of the Noise Level in the Colour Fundus Images",

abstract = "Diabetic Retinopathy (DR) causes vision loss insufficiency due to impediment rising from high sugar level conditions disturbing the retina. The Progression of DR occurs in the Foveal avascular zone (FAZ) due to loss of tiny blood vessels of capillary network. Due to image acquisition process of fundus camera, the colour retinal fundus image suffers from varying contrast and noise problems. To overcome varying contrast and noise problem in fundus image, the technique has been implemented. The technique is contained on the Retinex algorithm along with stationary wavelet transform. The technique has been applied on 36 high resolution fundus (HRF) image database contain the 18 bad quality images and 18 good quality images. The RETSWT (RETinex and Stationary Wavelet Transform) developed with introduces denoising techniques. Stationary wavelet transform is used as denoised technique. RETSWT achieved the average PSNR improvement of 2.39 db good quality images else it achieved the average PSNR improvement of 2.20 db in the bad quality images. The RETSWT image enhancement method potentially reduces the need of the invasive fluorescein angiogram in DR assessment",

keywords = "Acquisition process, Capillary network, De-noising techniques, Diabetic retinopathy, Engineering controlled terms: Blood vessels, Engineering main heading: Wavelet transforms, Eye protection, Foveal avascular zones, Image acquisition, Image enhancement, Noise pollution, Retinal fundus images, Retinex algorithms, Stationary wavelet transforms",

author = "Toufique Soomro and Junbin Gao",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = Springer Verlag, 2016. Event dates (773o) = August 8-9, 2015; Parent title (773t) = International Conference on Data Science. ISSNs: 0302-9743; ; International Conference on Data Science ; Conference date: 08-08-2015 Through 09-08-2015",

year = "2015",

doi = "10.1007/978-3-319-24474-7_22",

language = "English",

volume = "9208",

pages = "159--168",

booktitle = "ICDS 2015",

publisher = "Springer-Verlag London Ltd.",

address = "Germany",

url = "https://link.springer.com/book/10.1007/978-3-319-24474-7",

}

TY - GEN

T1 - Study of the Noise Level in the Colour Fundus Images

AU - Soomro, Toufique

AU - Gao, Junbin

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = Springer Verlag, 2016. Event dates (773o) = August 8-9, 2015; Parent title (773t) = International Conference on Data Science. ISSNs: 0302-9743;

PY - 2015

Y1 - 2015

N2 - Diabetic Retinopathy (DR) causes vision loss insufficiency due to impediment rising from high sugar level conditions disturbing the retina. The Progression of DR occurs in the Foveal avascular zone (FAZ) due to loss of tiny blood vessels of capillary network. Due to image acquisition process of fundus camera, the colour retinal fundus image suffers from varying contrast and noise problems. To overcome varying contrast and noise problem in fundus image, the technique has been implemented. The technique is contained on the Retinex algorithm along with stationary wavelet transform. The technique has been applied on 36 high resolution fundus (HRF) image database contain the 18 bad quality images and 18 good quality images. The RETSWT (RETinex and Stationary Wavelet Transform) developed with introduces denoising techniques. Stationary wavelet transform is used as denoised technique. RETSWT achieved the average PSNR improvement of 2.39 db good quality images else it achieved the average PSNR improvement of 2.20 db in the bad quality images. The RETSWT image enhancement method potentially reduces the need of the invasive fluorescein angiogram in DR assessment

AB - Diabetic Retinopathy (DR) causes vision loss insufficiency due to impediment rising from high sugar level conditions disturbing the retina. The Progression of DR occurs in the Foveal avascular zone (FAZ) due to loss of tiny blood vessels of capillary network. Due to image acquisition process of fundus camera, the colour retinal fundus image suffers from varying contrast and noise problems. To overcome varying contrast and noise problem in fundus image, the technique has been implemented. The technique is contained on the Retinex algorithm along with stationary wavelet transform. The technique has been applied on 36 high resolution fundus (HRF) image database contain the 18 bad quality images and 18 good quality images. The RETSWT (RETinex and Stationary Wavelet Transform) developed with introduces denoising techniques. Stationary wavelet transform is used as denoised technique. RETSWT achieved the average PSNR improvement of 2.39 db good quality images else it achieved the average PSNR improvement of 2.20 db in the bad quality images. The RETSWT image enhancement method potentially reduces the need of the invasive fluorescein angiogram in DR assessment

KW - Acquisition process

KW - Capillary network

KW - De-noising techniques

KW - Diabetic retinopathy

KW - Engineering controlled terms: Blood vessels

KW - Engineering main heading: Wavelet transforms

KW - Eye protection

KW - Foveal avascular zones

KW - Image acquisition

KW - Image enhancement

KW - Noise pollution

KW - Retinal fundus images

KW - Retinex algorithms

KW - Stationary wavelet transforms

UR - https://link.springer.com/content/pdf/bfm%3A978-3-319-24474-7%2F1.pdf

U2 - 10.1007/978-3-319-24474-7_22

DO - 10.1007/978-3-319-24474-7_22

M3 - Conference paper

VL - 9208

SP - 159

EP - 168

BT - ICDS 2015

PB - Springer-Verlag London Ltd.

T2 - International Conference on Data Science

Y2 - 8 August 2015 through 9 August 2015

ER -

Study of the Noise Level in the Colour Fundus Images

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this