Pyramidal stereo matching and optimal surface recovery for 3-D visualization

Three-dimensional surface recovery based on a pair of stereoscopic images is a very well-known ill-posed problem with solutions depending mainly on the correct measures of the shifts between corresponding points (disparities) in the images acquired by a known imaging system. Noise, occlusions, and distortion present in the pair of images make the task of finding precise disparities difficult and very time consuming.

This work presents a three-dimensional surface restoration method based on the recovery of the optimum surface within a 3-D cross-correlation coefficient volume via a two-stage dynamic programming technique. This procedure is applied to a set of optic nerve head (ONH) images, which are used for finding clinical measures of progression of glaucoma. Registration of these types of images is performed through a two-step coarse-to- fine procedure using power cepstrum and cross-correlation operations, while a local registration based on the weighted mean of second-degree polynomials is used for image fitting.

Variations in topography of the ONH can be measured through cup-to-disc ratios which are computed from the 3-D surface generated from longitudinal stereo disc photographs of glaucoma patients spanning several years. These computer-generated measures of cup-to-disc volume ratios correlate well with the traditional stereo cup-to-disc ratios manually computed from clinical interpretations.

Such algorithmic approach to semi-automated computation of cup-to-disc volume ratios may potentially provide a more precise and repeatable measure of progression of glaucoma than the existing clinical measures. Moreover, the 3-D surface recovery technique developed in this thesis may provide a general technique for visualizing 3-D objects in a natural scene.