Glaucoma is a disease in which fluid pressure in the eye increases continously, and damage the optic nerve and leads to vision loss.It is the second leading cause of blindness. For identification of disease in human eyes we are using clinical decision support system which is based on retinal image analysis technique,that used to extract structure,contextual or texture features.Texture features within images which gives accurate and efficicent glaucoma classification.For finding this texture features we use energy distribution over wavelet subband.In this paper we focus on fourteen features which is obtained from daubecies(db3),symlets(sym3),and biorthogonal(bio3.3,bio3.5,and bio3.7).We propose a novel technique to extract this energy signatures using 2- D wavelet transform and passed these signatures to different feature ranking and feature selection strategies.The energy obtained from detailed coefficent are used to classify normal and glaucomatous image with high accuracy. This will be classified using support vector machines, sequential minimal optimization, random forest, naive Bayes and artificial neural network.We observed an accuracy of 94% using the ANN classifier.Performance graph is shown for all classifiers.Finally the defected region founded by segmentation and this will be post processed by morphological processing technique for smoothing operation. Index Terms: Artificial neural network,data mining,feature extraction,glaucoma,imagetexture,wavelet transforms. I. Introduction GLAUCOMA is an eye disease and it is the second leading cause of peripheral blindness nowadays.This leads to neurodegeneration of the optic nerve.It is estiamted that above six million peoples have glaucoma(1),and half of them are unaware that they have this.Approximately 140000 are blind from glaucoma,about 5% of population between 40-50 yers old and 10% over 70 years old ,whcih increases the risk of significant vision loss. Glaucoma is normally associated with increased fluid pressure in the eye.It is divided into two types "open-angle and "closed-angle" glaucoma.Closed -angle glaucoma appears suddenly which is painful and also visual loss occurs quickly.Open-angle is a chronic glaucoma, It progresses at a slower rate and patients may not notice they have lost vision until the disease has increased significantly. In closed angle glaucoma, fluid pressure in the eye increases because of inadequate fluid flow between iris and the cornea. For the detection and pigmentation of glaucoma,effective quantitative imaging alternatives are offered in biomedical imaging.Eye images manually analysing is fairly time consuming,and the accuracy of parameter measurements varies between experts.Some of the prominent existing modalities and their enhancements,includes optical coherence tomography(2) and multifocal electroretinograph (mfERG) (3),are teh most prominent techniques employed for the quantitatively analyze stuctural and functional abnormalities in the eye,which will observe variability and to quantify the progresion of the disease. Automated clinical decision support system(CDSSs) in opthalmology(4),which are designed mainly for the identification of the disease pathology in human eyes.CDSSs are based on the retinal image analysis techniques that are used to extract structural,textural or contextual features from the images and it effectively distinguish between normal and diseased samples.Retinal image analysis technique which is mainly based on computational techniques to make qualitative checking of eye more objectively.Main goal behind this method is to , reduce the variability that may arising between different clinicla trackingsand for the progresion of the structural characteristics of the human eye. In CDSSs features extracted are categorized into two types structural features and texture features.In structural features commonly includes disk area ,disk diameter ,rim area,cup diameter,cup-to-disk ratio, and topological features extracted from the image(5).Proper orthogonal decomposistion technique (POD) which uses structural features to identify glaucomatous progression(6).Pixel level information is given by POD which is used to gauge significant changes across samples which is locatrion or region specific.The measurement of texture features, is roughly defined as spatial variation of pixel intensity.Texture featrures are not bound to any specific location on image.Several feature extraction techniques are there to mine texture features.From the experiments, we can say that texture based techniques have been proven successful.
Glaucoma Detection Using Dwt Based Energy Features and Ann Classifier
Published 2014 in IOSR Journal of Computer Engineering
ABSTRACT
PUBLICATION RECORD
- Publication year
2014
- Venue
IOSR Journal of Computer Engineering
- Publication date
Unknown publication date
- Fields of study
Medicine, Computer Science, Engineering
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-22 of 22 references · Page 1 of 1
CITED BY
Showing 1-5 of 5 citing papers · Page 1 of 1