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

Ananda S. Chowdhury, Suchendra M. Bhandarkar, Robert W. Robinson, Jack C Yu

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Pages (from-to)931-938
Number of pages8
JournalPattern Recognition Letters
Volume30
Issue number10
DOIs
StatePublished - Jul 15 2009

Fingerprint

Graph theory
Computer vision
Surface reconstruction
Tomography

Keywords

  • Bipartite graph matching
  • Computed Tomography
  • Graph automorphism
  • Hausdorff distance
  • ICP

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints. / Chowdhury, Ananda S.; Bhandarkar, Suchendra M.; Robinson, Robert W.; Yu, Jack C.

In: Pattern Recognition Letters, Vol. 30, No. 10, 15.07.2009, p. 931-938.

Research output: Contribution to journalArticle

Chowdhury, Ananda S. ; Bhandarkar, Suchendra M. ; Robinson, Robert W. ; Yu, Jack C. / Virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints. In: Pattern Recognition Letters. 2009 ; Vol. 30, No. 10. pp. 931-938.
@article{25464983456f433c852f8110be36e2ee,
title = "Virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints",
abstract = "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.",
keywords = "Bipartite graph matching, Computed Tomography, Graph automorphism, Hausdorff distance, ICP",
author = "Chowdhury, {Ananda S.} and Bhandarkar, {Suchendra M.} and Robinson, {Robert W.} and Yu, {Jack C}",
year = "2009",
month = "7",
day = "15",
doi = "10.1016/j.patrec.2009.03.010",
language = "English (US)",
volume = "30",
pages = "931--938",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "10",

}

TY - JOUR

T1 - Virtual craniofacial reconstruction using computer vision, graph theory and geometric constraints

AU - Chowdhury, Ananda S.

AU - Bhandarkar, Suchendra M.

AU - Robinson, Robert W.

AU - Yu, Jack C

PY - 2009/7/15

Y1 - 2009/7/15

N2 - 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.

AB - 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.

KW - Bipartite graph matching

KW - Computed Tomography

KW - Graph automorphism

KW - Hausdorff distance

KW - ICP

UR - http://www.scopus.com/inward/record.url?scp=67349269533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349269533&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2009.03.010

DO - 10.1016/j.patrec.2009.03.010

M3 - Article

AN - SCOPUS:67349269533

VL - 30

SP - 931

EP - 938

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 10

ER -