Fusion of matching algorithms for human identification using dental X-ray radiographs

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

The goal of forensic dentistry is to identify individuals based on their dental characteristics. In this paper, we introduce a system that uses some scenarios to fuse three matching techniques for identifying individuals based on their dental X-ray images. The system integrates a method for teeth segmentation, and three different methods for representing and matching teeth. The first method for matching antemortem (AM) and postmortem (PM) images represents each tooth contour by a set of signature vectors obtained at salient points on the contour of the tooth. The second method uses hierarchical chamfer distance for matching AM and PM teeth to reduce the search space and accordingly reduce the retrieval time. The third matching method represents each tooth by a small set of features extracted using the forcefield energy function and Fourier descriptors. For each matcher, given a query PM image, AM radiographs that are mostly similar to the PM image, are found and presented to the user. To improve the performance of the system, we present different scenarios to fuse the three matchers. We fuse the matchers using three different approaches at the matching level, the decision level, and using the Bayesian framework. Preliminarily results demonstrate that fusing the matching techniques improves the overall performance of the dental identification system.

Original languageEnglish
Article number4472862
Pages (from-to)223-233
Number of pages11
JournalIEEE Transactions on Information Forensics and Security
Volume3
Issue number2
DOIs
StatePublished - Jun 1 2008

Fingerprint

Electric fuses
Fusion reactions
X rays
Dentistry
Identification (control systems)

Keywords

  • Antemortem (AM) radiographs
  • Biometrics
  • Dental images
  • Force field
  • Forensic radiology
  • Fourier descriptors
  • Fusion
  • Human identification
  • Image segmentation
  • Postmortem (PM) radiographs

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Cite this

Fusion of matching algorithms for human identification using dental X-ray radiographs. / Nomir, Omaima; Abdel-Mottaleb, Mohamed.

In: IEEE Transactions on Information Forensics and Security, Vol. 3, No. 2, 4472862, 01.06.2008, p. 223-233.

Research output: Contribution to journalArticle

@article{c3ac3474a1944209ad0f8f81d9607e28,
title = "Fusion of matching algorithms for human identification using dental X-ray radiographs",
abstract = "The goal of forensic dentistry is to identify individuals based on their dental characteristics. In this paper, we introduce a system that uses some scenarios to fuse three matching techniques for identifying individuals based on their dental X-ray images. The system integrates a method for teeth segmentation, and three different methods for representing and matching teeth. The first method for matching antemortem (AM) and postmortem (PM) images represents each tooth contour by a set of signature vectors obtained at salient points on the contour of the tooth. The second method uses hierarchical chamfer distance for matching AM and PM teeth to reduce the search space and accordingly reduce the retrieval time. The third matching method represents each tooth by a small set of features extracted using the forcefield energy function and Fourier descriptors. For each matcher, given a query PM image, AM radiographs that are mostly similar to the PM image, are found and presented to the user. To improve the performance of the system, we present different scenarios to fuse the three matchers. We fuse the matchers using three different approaches at the matching level, the decision level, and using the Bayesian framework. Preliminarily results demonstrate that fusing the matching techniques improves the overall performance of the dental identification system.",
keywords = "Antemortem (AM) radiographs, Biometrics, Dental images, Force field, Forensic radiology, Fourier descriptors, Fusion, Human identification, Image segmentation, Postmortem (PM) radiographs",
author = "Omaima Nomir and Mohamed Abdel-Mottaleb",
year = "2008",
month = "6",
day = "1",
doi = "10.1109/TIFS.2008.919343",
language = "English",
volume = "3",
pages = "223--233",
journal = "IEEE Transactions on Information Forensics and Security",
issn = "1556-6013",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Fusion of matching algorithms for human identification using dental X-ray radiographs

AU - Nomir, Omaima

AU - Abdel-Mottaleb, Mohamed

PY - 2008/6/1

Y1 - 2008/6/1

N2 - The goal of forensic dentistry is to identify individuals based on their dental characteristics. In this paper, we introduce a system that uses some scenarios to fuse three matching techniques for identifying individuals based on their dental X-ray images. The system integrates a method for teeth segmentation, and three different methods for representing and matching teeth. The first method for matching antemortem (AM) and postmortem (PM) images represents each tooth contour by a set of signature vectors obtained at salient points on the contour of the tooth. The second method uses hierarchical chamfer distance for matching AM and PM teeth to reduce the search space and accordingly reduce the retrieval time. The third matching method represents each tooth by a small set of features extracted using the forcefield energy function and Fourier descriptors. For each matcher, given a query PM image, AM radiographs that are mostly similar to the PM image, are found and presented to the user. To improve the performance of the system, we present different scenarios to fuse the three matchers. We fuse the matchers using three different approaches at the matching level, the decision level, and using the Bayesian framework. Preliminarily results demonstrate that fusing the matching techniques improves the overall performance of the dental identification system.

AB - The goal of forensic dentistry is to identify individuals based on their dental characteristics. In this paper, we introduce a system that uses some scenarios to fuse three matching techniques for identifying individuals based on their dental X-ray images. The system integrates a method for teeth segmentation, and three different methods for representing and matching teeth. The first method for matching antemortem (AM) and postmortem (PM) images represents each tooth contour by a set of signature vectors obtained at salient points on the contour of the tooth. The second method uses hierarchical chamfer distance for matching AM and PM teeth to reduce the search space and accordingly reduce the retrieval time. The third matching method represents each tooth by a small set of features extracted using the forcefield energy function and Fourier descriptors. For each matcher, given a query PM image, AM radiographs that are mostly similar to the PM image, are found and presented to the user. To improve the performance of the system, we present different scenarios to fuse the three matchers. We fuse the matchers using three different approaches at the matching level, the decision level, and using the Bayesian framework. Preliminarily results demonstrate that fusing the matching techniques improves the overall performance of the dental identification system.

KW - Antemortem (AM) radiographs

KW - Biometrics

KW - Dental images

KW - Force field

KW - Forensic radiology

KW - Fourier descriptors

KW - Fusion

KW - Human identification

KW - Image segmentation

KW - Postmortem (PM) radiographs

UR - http://www.scopus.com/inward/record.url?scp=44049088552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44049088552&partnerID=8YFLogxK

U2 - 10.1109/TIFS.2008.919343

DO - 10.1109/TIFS.2008.919343

M3 - Article

AN - SCOPUS:44049088552

VL - 3

SP - 223

EP - 233

JO - IEEE Transactions on Information Forensics and Security

JF - IEEE Transactions on Information Forensics and Security

SN - 1556-6013

IS - 2

M1 - 4472862

ER -