STUDY OF IMAGE SEGMENTATION TECHNIQUES ON RETINAL IMAGES FOR HEALTH CARE MANAGEMENT WITH FAST COMPUTING
Abstract
vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff22510a0000006b0f000001000b00
The role of segmentation in image processing is to separate foreground from background. In this process, the features become clearly visible when appropriate filters are applied on the image. In this paper emphasis has been laid on segmentation of biometric retinal images to filter out the vessels explicitly for evaluating the bifurcation points and features for diabetic retinopathy. Segmentation on images is performed by calculating ridges or morphology. Ridges are those areas in the images where there is sharp contrast in features. Morphology targets the features using structuring elements. Structuring elements are of different shapes like disk, line which is used for extracting features of those shapes. When segmentation was performed on retinal images problems were encountered during image pre-processing stage. Also edge detection techniques have been deployed to find out the contours of the retinal images. After the segmentation has been performed, it has been seen that artifacts of the retinal images have been minimal when ridge based segmentation technique was deployed. In the field of Health Care Management, image segmentation has an important role to play as it determines whether a person is normal or having any disease specially diabetes. During the process of segmentation, diseased features are classified as diseased one’s or artifacts. The problem comes when artifacts are classified as diseased ones. This results in misclassification which has been discussed in the analysis Section. We have achieved fast computing with better performance, in terms of speed for non-repeating features, when compared to repeating features.

Authors
Srikanth Prabhu1 N. Gopalakrishna Kini2
Manipal Institute of Technology, Manipal University, India

Keywords
Pupil, Sclera, Limbus, Diabetes, Micro- Aneurysms, Exudates, Gabor, Log, Bifurcation, Sobel, Gray Level, Decision Tree, KNN
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
000000000000
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 2 , Issue: 3 , Pages: 352-356 )
Date of Publication :
February 2012
Page Views :
141
Full Text Views :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.