Motivated by the problem of retinal image registration, this paper introduces and analyzes a new registration algorithm called Dual-Bootstrap Iterative Closest Point (Dual-Bootstrap ICP). The approach is to start from one or more initial, low-order estimates that are only accurate in small image regions, called bootstrap regions. In each bootstrap region, the algorithm iteratively: 1) refines the transformation estimate using constraints only from within the bootstrap region; 2) expands the bootstrap region; and 3) tests to see if a higher order transformation model can be used, stopping when the region expands to cover the overlap between images. Steps 1): and 3), the bootstrap steps, are governed by the covariance matrix of the estimated transformation. Estimation refinement [Step 2)] uses a novel robust version of the ICP algorithm. In registering retinal image pairs, Dual-Bootstrap ICP is initialized by automatically matching individual vascular landmarks, and it aligns images based on detected blood vessel centerlines. The resulting quadratic transformations are accurate to less than a pixel. On tests involving approximately 6000 image pairs, it successfully registered 99.5% of the pairs containing at least one common landmark, and 100% of the pairs containing at least one common landmark and at least 35% image overlap.

No abstract

Abstract. Estimation techniques in computer vision applications must estimate accurate model parameters despite small-scale noise in the data, occasional large-scale measurement errors (outliers), and measurements from multiple populations in the same data set. Increasingly, robust estimation techniques, some borrowed from the statistics literature and others described in the computer vision literature, have been used in solving these parameter estimation problems. Ideally, these techniques should effectively ignore the outliers and measurements from other populations, treating them as outliers, when estimating the parameters of a single population. , 1981]. LMS handles large fractions of outliers, up to the theoretical limit of 50% for estimators invariant to affine changes to the data, but has low statistical efficiency. M-estimators have higher statistical efficiency but tolerate much lower percentages of outliers unless properly initialized. While robust estimators have been used in a variety of computer vision applications, three are considered here. In analysis of range images-images containing depth or X, Y , Z measurements at each pixel instead of intensity measurements-robust estimators have been used successfully to estimate surface model parameters in small image regions. In stereo and motion analysis, they have been used to estimate parameters of what is called the "fundamental matrix," which characterizes the relative imaging geometry of two cameras imaging the same scene. Recently, robust estimators have been applied to estimating a quadratic image-to-image transformation model necessary to create a composite, "mosaic image" from a series of images of the human retina. In each case, a straightforward application of standard robust estimators is insufficient, and carefully developed extensions are used to solve the problem.

ÐThis paper describes a robust hierarchical algorithm for fully-automatic registration of a pair of images of the curved human retina photographed by a fundus microscope. Accurate registration is essential for mosaic synthesis, change detection, and design of computer-aided instrumentation. Central to the new algorithm is a 12-parameter interimage transformation derived by modeling the retina as a rigid quadratic surface with unknown parameters, imaged by an uncalibrated weak perspective camera. The parameters of this model are estimated by matching vascular landmarks extracted by an algorithm that recursively traces the blood vessel structure. The parameter estimation technique, which could be generalized to other applications, is a hierarchy of models and methods: an initial match set is pruned based on a zeroth order transformation estimated as the peak of a similarity-weighted histogram; a first order, affine transformation is estimated using the reduced match set and least-median of squares; and the final, second order, 12-parameter transformation is estimated using an M-estimator initialized from the first order estimate. This hierarchy makes the algorithm robust to unmatchable image features and mismatches between features caused by large interframe motions. Before final convergence of the M-estimator, feature positions are refined and the correspondence set is enhanced using normalized sum-of-squared differences matching of regions deformed by the emerging transformation. Experiments involving 3,000 image pairs (I; HPR Â I; HPR pixels) from 16 different healthy eyes were performed. Starting with as low as 20 percent overlap between images, the algorithm improves its success rate exponentially and has a negligible failure rate above 67 percent overlap. The experiments also quantify the reduction in errors as the model complexities increase. Final registration errors less than a pixel are routinely achieved. The speed, accuracy, and ability to handle small overlaps compare favorably with retinal image registration techniques published in the literature.

No abstract

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at non-vascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matchedfilter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a 6-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an efficient and effective vessel centerline extraction algorithm.

Abstract-Our goal is an automated 2D-image-pair registration algorithm capable of aligning images taken of a wide variety of natural and man-made scenes as well as many medical images. The algorithm should handle low overlap, substantial orientation and scale differences, large illumination variations, and physical changes in the scene. An important component of this is the ability to automatically reject pairs that have no overlap or have too many differences to be aligned well. We propose a complete algorithm including techniques for initialization, for estimating transformation parameters, and for automatically deciding if an estimate is correct. Keypoints extracted and matched between images are used to generate initial similarity transform estimates, each accurate over a small region. These initial estimates are rank-ordered and tested individually in succession. Each estimate is refined using the Dual-Bootstrap ICP algorithm, driven by matching of multiscale features. A three-part decision criteria, combining measurements of alignment accuracy, stability in the estimate, and consistency in the constraints, determines whether the refined transformation estimate is accepted as correct. Experimental results on a data set of 22 challenging image pairs show that the algorithm effectively aligns 19 of the 22 pairs and rejects 99.8 percent of the misalignments that occur when all possible pairs are tried. The algorithm substantially out-performs algorithms based on keypoint matching alone.

No abstract