Automated 3-D reconstruction of stereo fundus images via camera calibration and image rectification

Glaucoma is one of the leading causes of vision loss in the United States, and through early diagnosis and continued monitoring it is possible to delay or even stop the progression of the disease. An automated algorithm for estimating cup to disc ratios, a quantity that is key to tracking glaucoma progression, has already been developed and shown to have high correlation to physician-generated measures over a period of many years. The algorithm in its current state uses image warping to produce aligned stereo pairs that can then be used to estimate depth in the image. In this work, the warping algorithm has been replaced with a more direct camera geometry estimation algorithm. This improvement will allow the images to then be rectified, or transformed into the ideal stereo camera geometry, which greatly simplifies the disparity map generation and automated analysis segments of the existing algorithm.