Abstract | ||
---|---|---|
Motivated by the observation that a retinal fundus image may contain some unique geometric structures within its vascular trees which can be utilized for feature matching, in this paper, we proposed a graph-based registration framework called GM-ICP to align pairwise retinal images. First, the retinal vessels are automatically detected and represented as vascular structure graphs. A graph matching is then performed to find global correspondences between vascular bifurcations. Finally, a revised ICP algorithm incorporating with quadratic transformation model is used at fine level to register vessel shape models. In order to eliminate the incorrect matches from global correspondence set obtained via graph matching, we proposed a structure-based sample consensus (STRUCT-SAC) algorithm. The advantages of our approach are threefold: (1) global optimum solution can be achieved with graph matching; (2) our method is invariant to linear geometric transformations; and (3) heavy local feature descriptors are not required. The effectiveness of our method is demonstrated by the experiments with 48 pairs retinal images collected from clinical patients. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1155/2010/906067 | Int. J. Biomedical Imaging |
Keywords | Field | DocType |
global correspondence,vascular structure graph,retinal fundus image registration,global optimumsolution,retinal fundus image,pairwise retinal image,pairs retinal image,vascular bifurcation,feature matching,retinal vessel,vascular structure graph matching,graph matching,image registration | Computer vision,Pairwise comparison,Computer science,Transformation geometry,Quadratic equation,Vascular structure,Matching (graph theory),Artificial intelligence,Invariant (mathematics),Retinal,Fundus image | Journal |
Volume | ISSN | Citations |
2010 | 1687-4196 | 26 |
PageRank | References | Authors |
0.98 | 30 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kexin Deng | 1 | 55 | 3.05 |
Jie Tian | 2 | 1475 | 159.24 |
Jian Zheng | 3 | 26 | 0.98 |
Xing Zhang | 4 | 109 | 6.74 |
Xiaoqian Dai | 5 | 49 | 2.15 |
Min Xu | 6 | 45 | 5.45 |