Detection of fundus hard exudate based on IHBMO-RF

Tao Jing; Shaui Ren Jun; Wu Meng Lin; Liu Hong Lin

doi:10.1117/12.2532437

6 May 2019 Detection of fundus hard exudate based on IHBMO-RF

Tao Jing, Shaui Ren Jun, Wu Meng Lin, Liu Hong Lin

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110692Y (2019) https://doi.org/10.1117/12.2532437
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

Accurately identifying the location of hard exudate in retinal fundus helps to reduce the risk of blindness caused by diabetic retinopathy. An approach based on IHBMO-RF was proposed for hard exudate detection. The preprocessing procedure contains brightness correction, nonlinear wavelet denoising and high-hat filter enhancement. We used 2D Gaussian matched filter to locate the center of the optic disc and eliminate it. Secondly, the morphological methods were applied to obtain exudate candidate areas. Finally, the candidate regions were classified by using the IHBMO-RF algorithm to extract the final and accurate hard exudate. This method was tested in the published DiaretDB1 fundus image database and the accuracy of extraction of hard exudate was 96.8%. The experiment shows that based on the IHBMO-RF algorithm can accurately identify the position of hard exudate in fundus images and has good robust performance.

Citation Download Citation

Tao Jing, Shaui Ren Jun, Wu Meng Lin, and Liu Hong Lin "Detection of fundus hard exudate based on IHBMO-RF", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110692Y (6 May 2019); https://doi.org/10.1117/12.2532437

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available