Validation of Retinal Image Registration Algorithms by a Projective Imaging Distortion Model

Fundus camera imaging of the retina is widely used to document ophthalmologic disorders including diabetic retinopathy, glaucoma, and age-related macular degeneration. The retinal images typically have a limited field of view due mainly to the curvedness of human retina, so multiple images are to be joined together using image registration technique to form a montage with a larger field of view. A variety of methods for retinal image registration have been proposed, but evaluating such methods objectively is difficult due to the lack of a reference standard for the true alignment of the individual images that make up the montage. A method of generating simulated retinal image set by modeling geometric distortions due to the eye geometry and the image acquisition process is described in this paper. We also present the validation tool for any retinal image registration method by tracing back the distortion path and accessing the geometric misalignment from the coordinate system of reference standard. The quantitative comparison for different registration methods is given in the experiment, so the registration performance is evaluated in an objective manner.