Please use this identifier to cite or link to this item: http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/5621
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKaushal, Shilpa-
dc.contributor.authorJain, Shruti [Guided by]-
dc.contributor.authorSharma, Sunil Datt [Guided by]-
dc.date.accessioned2022-08-05T10:15:30Z-
dc.date.available2022-08-05T10:15:30Z-
dc.date.issued2018-
dc.identifier.urihttp://ir.juit.ac.in:8080/jspui//xmlui/handle/123456789/5621-
dc.description.abstractGlaucoma, a multi factor optical neuropathy, harms the optic nerve fibers impairing the vision and finally leads to blindness. Often titled as 'The sneak thief of Sight', Glaucoma has no significantly identifiable symptoms until considerable vision loss has occurred. Affecting one in every two hundred of the population younger than fifty and one in ten in the population aged above eighty, Glaucoma ranks second in the count of diseases causing blindness all around the globe. In the present scenario of technological and medical advancements, Computer vision and image processing form an imperative field of modern Ophthalmology. Medical imaging has delved into the deepest corners of the field and provided efficient healthcare services at appropriate prices in almost all disease areas. The less invasive techniques provided by medical imaging provides scientists and physicians with important information that could be life-saving. New imaging techniques used for retinal analysis are computationally complex, expensive and have poor performance parameters. Therefore, there is a need to be develop a less expensive, low computational complex, non-invasive and efficient method for the detection of Glaucoma. The objective of this work is to emphasize on the signal processing methods for the early detection of Glaucoma. This study aims to automatically differentiate fundus images of normal eye from Glaucoma eye on the basis of structural feature and distribution of textures. The method used for the detection of Glaucoma is based on empirical wavelet transform (EWT). Decomposition of image is done using EWT and correntropy values are calculated from these decomposed components. These extracted features are ranked based on student t-test value. Then, these features are used for the classification of normal and glaucoma images using SVM classifier. We have compared results of different types of EWT Transforms i.e. EWT 2D Little-wood Paley, EWT 2D Curvelet, EWT 2D Ridgelet and EWT 2D Tensor.en_US
dc.language.isoenen_US
dc.publisherJaypee University of Information Technology, Solan, H.P.en_US
dc.subjectGlaucomaen_US
dc.subjectEmpirical wavelet transformen_US
dc.subjectDiscrete wavelet transformen_US
dc.subjectArtificial neural networken_US
dc.subjectGenetic algorithmen_US
dc.titleEvaluation of Empirical Wavelet Transforms for Glaucoma Detection Using Fundus Imagesen_US
dc.typeProject Reporten_US
Appears in Collections:Dissertations (M.Tech.)

Files in This Item:
File Description SizeFormat 
Evaluation of Empirical Wavelet Transforms for Glaucoma Detection Using Fundus Images.pdf4.05 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.