Face recognition based on 3D ridge images obtained from range data

Mohammad H. Mahoor, Mohamed Abdel-Mottaleb

Research output: Contribution to journalArticle

73 Citations (Scopus)

Abstract

In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, kmax, to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.

Original languageEnglish
Pages (from-to)445-451
Number of pages7
JournalPattern Recognition
Volume42
Issue number3
DOIs
StatePublished - Mar 1 2009

Fingerprint

Face recognition
Binary images
Experiments

Keywords

  • 3D face recognition
  • Gaussian curvature
  • Hausdorff distance
  • Iterative closest points
  • Range image
  • Ridge image

ASJC Scopus subject areas

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

Cite this

Face recognition based on 3D ridge images obtained from range data. / Mahoor, Mohammad H.; Abdel-Mottaleb, Mohamed.

In: Pattern Recognition, Vol. 42, No. 3, 01.03.2009, p. 445-451.

Research output: Contribution to journalArticle

@article{1b144ec704544a93bcd87f7f562ad3ed,
title = "Face recognition based on 3D ridge images obtained from range data",
abstract = "In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, kmax, to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.",
keywords = "3D face recognition, Gaussian curvature, Hausdorff distance, Iterative closest points, Range image, Ridge image",
author = "Mahoor, {Mohammad H.} and Mohamed Abdel-Mottaleb",
year = "2009",
month = "3",
day = "1",
doi = "10.1016/j.patcog.2008.08.012",
language = "English",
volume = "42",
pages = "445--451",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Face recognition based on 3D ridge images obtained from range data

AU - Mahoor, Mohammad H.

AU - Abdel-Mottaleb, Mohamed

PY - 2009/3/1

Y1 - 2009/3/1

N2 - In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, kmax, to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.

AB - In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, kmax, to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.

KW - 3D face recognition

KW - Gaussian curvature

KW - Hausdorff distance

KW - Iterative closest points

KW - Range image

KW - Ridge image

UR - http://www.scopus.com/inward/record.url?scp=54549086449&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54549086449&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2008.08.012

DO - 10.1016/j.patcog.2008.08.012

M3 - Article

AN - SCOPUS:54549086449

VL - 42

SP - 445

EP - 451

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 3

ER -