Welcome to the InfoSci Platform
Reference Hub2
Retinal Blood Vessel Segmentation Using a Generalized Gamma Probability Distribution Function (PDF) of Matched Filtered

Retinal Blood Vessel Segmentation Using a Generalized Gamma Probability Distribution Function (PDF) of Matched Filtered

K Susheel Kumar, Nagendra Pratap Singh
Copyright: © 2022 |Volume: 11 |Issue: 2 |Pages: 16
ISSN: 2156-177X|EISSN: 2156-1761|EISBN13: 9781683182504|DOI: 10.4018/IJFSA.296693
Cite Article Cite Article

MLA

K Susheel Kumar, and Nagendra Pratap Singh. "Retinal Blood Vessel Segmentation Using a Generalized Gamma Probability Distribution Function (PDF) of Matched Filtered." IJFSA vol.11, no.2 2022: pp.1-16. http://doi.org/10.4018/IJFSA.296693

APA

K Susheel Kumar & Singh, N. P. (2022). Retinal Blood Vessel Segmentation Using a Generalized Gamma Probability Distribution Function (PDF) of Matched Filtered. International Journal of Fuzzy System Applications (IJFSA), 11(2), 1-16. http://doi.org/10.4018/IJFSA.296693

Chicago

K Susheel Kumar, and Nagendra Pratap Singh. "Retinal Blood Vessel Segmentation Using a Generalized Gamma Probability Distribution Function (PDF) of Matched Filtered," International Journal of Fuzzy System Applications (IJFSA) 11, no.2: 1-16. http://doi.org/10.4018/IJFSA.296693

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Retinal images contain information about the retina's blood vessel structure to predict retinal diseases such as diabetics, obesity, glaucoma, etc. Segmentation of accurate retinal blood vessels is a challenging task in the low background of retinal images. Therefore, we proposed a Generalized Gamma Distribution probability distribution function (pdf) to extract the accurate vascular structure on the retinal images. The proposed approach is divided into processing steps, the Generalized Gamma distribution kernel, and the postprocessing step. In pre-processing, the conversion of a color retinal image into a grayscale image using PCA followed by the CLAHE method and the Toggle Contrast method enhances the grayscale images of the retina. The proposed matched filter of Generalized Gamma distribution generates the MFR images. The postprocessing step extracts the thick vessels and thin retinal blood vessels using the optimal thresholding technique. The results obtained on DIRVE database average accuracy 95.00% and the STARE database 93.85%, respectively.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.