Covariance-driven mosaic formation from sparsely-overlapping image sets with application to retinal image mosaicing

A new technique is presented for mosaicing sparsely-overlapping image sets, with a target application of assisting the diagnosis and treatment of retinal diseases. The geometric image transformations required to construct the mosaics are estimated by (1) estimating the transformations between as many pairs of images as possible, (2) extracting sets of constraints (correspondences)from the successfully registered image pairs, and (3) using these constraint sets to simultaneously (jointly) estimate the final transformations. Unfortunately, this may not be sufficient to construct seamless mosaics when two images overlap but can not be successfully registered (step 1). This paper presents a new method to generate constraints between such image pairs, and use these constraints to estimate a more consistent set of transformations. For each pair transformation parameter covariance matrices are computed and used to estimate the mapping error covariance matrices for individual features from one image. These features are matched in the second image by minimizing the resulting Mahalanobis distance. The generated correspondences are validated using robust estimation techniques and used to refine the estimates. The steps of covariance computation, matching, and transform estimation are repeated for all relevant image pairs until the final alignment converges. Results are presented and evaluated for several difficult image sets to illustrate the efficacy of the techniques.