Fundus images of the retina are color images of the eye taken by specially designed digital
cameras. Ophthalmologists rely on fundus images to diagnose various diseases that affect the
eye such as diabetic retinopathy and retinopathy of prematurity. A crucial preliminary step in
the analysis of retinal images is the identification and localization of important anatomical
structures such as the optic nerve head (ONH) the macula and the major vascular arcades.
Identification of the ONH is an important initial step in the detection and analysis of the
anatomical structures and pathological features in the retina. Different types of retinal
pathology may be detected and analyzed via the application of appropriately designed techniques
of digital image processing and pattern recognition. Computer-aided analysis of retinal images
has the potential to facilitate quantitative and objective analysis of retinal lesions and
abnormalities. Accurate identification and localization of retinal features and lesions could
contribute to improved diagnosis treatment and management of retinopathy. This book presents
an introduction to diagnostic imaging of the retina and an overview of image processing
techniques for ophthalmology. In particular digital image processing algorithms and pattern
analysis techniques for the detection of the ONH are described. In fundus images the ONH
usually appears as a bright region white or yellow in color and is indicated as the
convergent area of the network of blood vessels. Use of the geometrical and intensity
characteristics of the ONH as well as the property that the ONH represents the location of
entrance of the blood vessels and the optic nerve into the retina is demonstrated in
developing the methods. The image processing techniques described in the book include
morphological filters for preprocessing fundus images filters for edge detection the Hough
transform for the detection of lines and circles Gabor filters to detect the blood vessels
and phase portrait analysis for the detection of convergent or node-like patterns.
Illustrations of application of the methods to fundus images from two publicly available
databases are presented in terms of locating the center and the boundary of the ONH. Methods
for quantitative evaluation of the results of detection of the ONH using measures of overlap
and free-response receiver operating characteristics are also described. Table of Contents:
Introduction Computer-aided Analysis of Images of the Retina Detection of Geometrical
Patterns Datasets and Experimental Setup Detection of theOptic Nerve HeadUsing the Hough
Transform Detection of theOptic Nerve HeadUsing Phase Portraits Concluding Remarks
