Bonfring International Journal of Advances in Image Processing
Online ISSN: 2277-503X | Print ISSN: 2250-1053 | Frequency: 4 Issues/Year
Impact Factor: 0.245 | International Scientific Indexing(ISI) calculate based on International Citation Report(ICR)
Fovea Localisation in Fundus Image using Adaptive Morphology
K.A. Nyni and T. Vandarkuzhali
Abstract:
As digital imaging and computing power is developing day by day, so too does the potential to use these technologies in ophthalmology. Image processing, analysis and computer vision techniques are increasing in prominence in all fields of medical science, and are especially unavoidable in modern ophthalmology, as it is heavily dependent on visually oriented signs. The developments in image processing that is relevant to ophthalmology over the past 15 years includes the progress being made towards developing automated diagnostic systems for conditions, such as diabetic retinopathy, age-related macular degeneration and retinopathy of prematurity. Retinal image analysis is one of the leading topics in medical image processing. The detection of the fovea position in fundus retinal image is an important aspect of medical image processing. In manual analysis, due to unavailability of trained ophthalmologists, the diagnosis of retinal diseases becomes unclear. Thus, automatic analysis of fundus image is very much essential and will help to facilitate clinical diagnosis. An automatic system for the detection of various features of retinal image which includes the blood vessels, optic disc, macula and fovea is carried out by morphological operations. Fovea is one of the important features of a fundus retinal image which is characterized by the center of macula. The algorithm consists of various morphological operations and finally localisation of fovea. The main contributions are: Time consumption for detection of the fovea region is very less when compared to manual detection. It is simple and efficient in extracting the fovea region accurately. It performs well on our own data set consisting of images with various characteristics and is robust also. The extracted fovea region will help in further diagnosis of related eye diseases by ophthalmologists. A high-performance language for technical computing, MATLAB, is used here to implement the concept. It integrates computation, visualization, and programming in an easy-to-use environment where problems and solutions are expressed in familiar mathematical notation. MATLAB is an interactive system whose basic data element is an array that does not require dimensioning. This helps to solve many technical computing problems, especially those with matrix and vector formulations, in a fraction of time. The work is implemented in Graphical User Interface (GUI) environment.
Keywords: Blood Vessels, Optic Disc, Macula, Fovea, Morphology, Ophthalmology, GUI
Volume: 2 | Issue: Special Issue on Communication Technology Interventions for Rural and Social Development
Pages: 80-85
Issue Date: February , 2012
|