Abstract

Glaucoma is an ocular disease caused by damaged optic nerve head (ONH) due to high intraocular pressure (IOP) within the eyeball. Usually, glaucoma patients will not realize the presence of this disease due to lack of visible early symptoms such as pain and redness mark. The disease can cause permanent blindness if it is not treated immediately. Hence, glaucoma screening is very crucial in detecting the disease during the early stages. There are various types of glaucoma screening tests such as tonometry test which is based on IOP measurement, ophthalmology test which is based on shape and color of the eyes, and pachymetry test which is based on complete field vision measurement. All these three screening tests involve manual assessment which is time-consuming and costly. Therefore, an efficient glaucoma screening system that can automatically analyze the severity level of the disease is very much needed. Thus, the main objective of this paper is to develop an automatic glaucoma screening system based on superpixel classification by providing a high-quality input image. Firstly, input images are undergone preprocessing methods to cater for noise removal and illumination correction. This is emphasized in the implementation of the anisotropic diffusion filter and illumination correction method. The pixels of the input images are then aggregate into superpixels using Simple Linear Iterative Clustering (SLIC) approach. Then, image features based on histogram data and textural information are extracted on each superpixel using statistical pixel-level (SPL) method. The prominent features are then fed into Support Vector Machine (SVM) classifier to classify each superpixel into optic disc, optic cup, blood vessel, and background regions. The classifier is also used to determine the boundaries of both optic disc and optic cup. Lastly, the segmented optic disc and optic cup are used to determine the presence of glaucoma using cup-to-disc ratio (CDR) measurement. The proposed method has been tested on RIM-One database. The experimental results have successfully distinguished optic disc and optic cup from the background with an average accuracy and sensitivity of 98.6% and 92.3%, respectively tested on linear kernel.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.