distinguishing of retinal area using slic based super pixel segmentation with svm classifier

P.Kannya,S.Kayathri,M.Nithila,R.K.Santhia

Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology

ISSN: 2321-3337          Impact Factor:1.521         Volume:4         Issue:3         Year: 09 April,2016         Pages:965-975

International Journal of Advanced Research in Computer Science Engineering and Information Technology

Abstract

Dynamic Scanning laser ophthalmoscopes SLOs can be utilized for ahead of schedule recognition of retinal sicknesses. With the appearance of most recent screening innovation, the upside of utilizing SLO is its wide field of perspective, which can picture an expansive part of the retina for better conclusion of the retinal sicknesses. Then again, amid the imaging process, ancient rarities, for example, eyelashes and eyelids are additionally imaged alongside the retinal zone. This brings a major test on the most proficient method to reject these relics. In this paper, we propose a novel methodology to naturally extricate out genuine retinal range from a SLO picture in light of picture handling and machine learning approaches. To decrease the unpredictability of picture preparing errands and give a advantageous primitive picture design, we have gathered pixels into distinctive districts taking into account the provincial size and minimization, called super pixels. The structure then ascertains picture based elements reflecting textural and basic data and characterizes between retinal region and ancient rarities.

Kewords

Feature choice, retinal curios extraction, retinal picture examination, filtering laser ophthalmoscope.

Reference

1.M. S. Haleem, L. Han, J. van Hemert, and B. Li, Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis A review Comput. Med. Imag. Graph., vol. 37, pp. 581.596, 2013. 2. M. J. Aligholizadeh, S. Javadi, R. S. Nadooshan, and K. Kangarloo, Eyelid and eyelash segmentation based on wavelet transform for iris recognition, inProc. 4th Int. Congr. Image Signal Process., 2011, pp. 1231. 1235.