Registration of challenging image pairs: initialization, estimation, and decision Gehua Yang Charles V. Stewart Michal Sofka Chia-Ling Tsai Image registration Feature extraction Iterative closest point 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 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 rank-ordered initial estimates are 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 suite of 22 challenging image pairs show that the algorithm effectively aligns 19 of the 22 pairs and rejects 99.8% misalignments when all possible pairs are tried. The algorithm substantially out-performs algorithms based on keypoint matching alone. Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY cs-05-19
Registration of challenging image pairs: initialization, estimation, and decision
Gehua Yang
Charles V. Stewart
Michal Sofka
Chia-Ling Tsai
Image registration
Feature extraction
Iterative closest point
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 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 rank-ordered initial estimates are 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 suite of 22 challenging image pairs show that the algorithm effectively aligns 19 of the 22 pairs and rejects 99.8% misalignments when all possible pairs are tried. The algorithm substantially out-performs algorithms based on keypoint matching alone.
Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY
cs-05-19