A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina

DMCA

A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Ali Can , Charles V. Stewart , Badrinath Roysam , Howard L. Tanenbaum

Venue:	IEEE Transactions on Pattern Analysis and Machine Intelligence
Citations:	68 - 18 self

BibTeX

@ARTICLE{Can02afeature-based,,
    author = {Ali Can and Charles V. Stewart and Badrinath Roysam and Howard L. Tanenbaum},
    title = {A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year = {2002},
    volume = {24},
    pages = {347--364}
}

OpenURL

Abstract

AbstractÐThis 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 newalgorithm 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 �1; 024 1; 024 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

Keyphrases

curved human retina hierarchical algorithm percent overlap correspondence set similarity-weighted histogram parameter estimation technique computer-aided instrumentation 12-parameter interimage transformation affine transformation second order blood vessel structure reduced match set 12-parameter transformation normalized sum-of-squared difference different healthy eye change detection first order unknown parameter unmatchable image feature initial match set image pair final convergence mosaic synthesis fully-automatic registration model complexity increase large interframe motion first order estimate negligible failure rate uncalibrated weak perspective camera feature position robust hierarchical algorithm fundus microscope vascular landmark success rate algorithm robust m-estimator initialized final registration error accurate registration zeroth order transformation rigid quadratic surface

DMCA