Share Email Print

Proceedings Paper

Detection of fundus hard exudate based on IHBMO-RF
Author(s): Tao Jing; Shaui Ren Jun; Wu Meng Lin; Liu Hong Lin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 6 May 2019
PDF: 8 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110692Y (6 May 2019); doi: 10.1117/12.2532437
Show Author Affiliations
Tao Jing, Nanjing Technology Univ. (China)
Shaui Ren Jun, Nanjing Technology Univ. (China)
Wu Meng Lin, Nanjing Technology Univ. (China)
Liu Hong Lin, Nanjing Technology Univ. (China)

Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?