Share Email Print
cover

Proceedings Paper

Statistical classifiers on local binary patterns for optical diagnosis of diabetic retinopathy
Author(s): Sabyasachi Mukhopadhyay; Sawon Pratiher; Sukanya Mukherjee; Gautham Pasupuleti; Ritwik Barman; Jay Chhablani; Prasanta K. Panigrahi
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Diabetic retinopathy damages retina due to diabetes mellitus which leads to blindness. Here, we have applied local binary pattern (LBP) in order to capture the spatial variations of the refractive indices due to progress of diabetic retinopathy among retinal tissues. After extraction of discriminative textures as binary numbers, state of art machine learning algorithms like decision tree and K-NN have been applied to get the optimum detection accuracy in multiclass classifications of in vivo diabetic retinopathy images. Here it is quite apparent that K-NN provides better accuracy and specificity than decision tree.

Paper Details

Date Published: 17 May 2018
PDF: 4 pages
Proc. SPIE 10685, Biophotonics: Photonic Solutions for Better Health Care VI, 106852Y (17 May 2018); doi: 10.1117/12.2305447
Show Author Affiliations
Sabyasachi Mukhopadhyay, Indian Institute of Science Education and Research Kolkata (India)
Sawon Pratiher, Indian Institute ofTechnology Kharagpur (India)
Sukanya Mukherjee, Univ. of Engineering & Management (India)
Gautham Pasupuleti, Biodesign Innovation Labs. Pvt. Ltd. (India)
Ritwik Barman, Indian Institute of Science Education and Research Kolkata (India)
Jay Chhablani, L.V. Prasad Eye Institute (India)
Prasanta K. Panigrahi, Indian Institute of Science Education and Research Kolkata (India)


Published in SPIE Proceedings Vol. 10685:
Biophotonics: Photonic Solutions for Better Health Care VI
Jürgen Popp; Valery V. Tuchin; Francesco Saverio Pavone, Editor(s)

© SPIE. Terms of Use
Back to Top