Virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints

A novel solution to the problem of virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints is proposed. Virtual craniofacial reconstruction is modeled along the lines of the well-known problem of rigid surface registration. The Iterative Closest Point (ICP)...

Full description

Saved in:
Bibliographic Details
Published inPattern recognition letters Vol. 30; no. 10; pp. 931 - 938
Main Authors Chowdhury, Ananda S., Bhandarkar, Suchendra M., Robinson, Robert W., Yu, Jack C.
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 15.07.2009
Elsevier
Subjects
Applied sciences
Artificial intelligence
Bipartite graph matching
Computed Tomography
Computer science; control theory; systems
Exact sciences and technology
Graph automorphism
Hausdorff distance
ICP
Image processing
Information, signal and communications theory
Pattern recognition. Digital image processing. Computational geometry
Signal processing
Telecommunications and information theory
Hausdorff distance
Computed Tomography
Bipartite graph matching
Graph automorphism
ICP
Automorphism
Computer vision
Computer theory
Image processing
Iterative method
Fracture
Graph theory
Algorithm
Image reconstruction
Computerized tomography
Conceptual graph
Surface reconstruction
Accuracy
Bipartite graph
Cycle(graph)
Graph matching
Online AccessGet full text

Cover

More Information
Summary:A novel solution to the problem of virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints is proposed. Virtual craniofacial reconstruction is modeled along the lines of the well-known problem of rigid surface registration. The Iterative Closest Point (ICP) algorithm is first employed with the closest set computation performed using the Maximum Cardinality Minimum Weight (MCMW) bipartite graph matching algorithm. Next, the bounding boxes of the fracture surfaces, treated as cycle graphs, are employed to generate multiple candidate solutions based on the concept of graph automorphism. The best candidate solution is selected by exploiting local and global geometric constraints. Finally, the initialization of the ICP algorithm with the best candidate solution is shown to improve surface reconstruction accuracy and speed of convergence. Experimental results on Computed Tomography (CT) scans of real patients are presented.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2009.03.010