Face recognition by elastic bunch graph matching

Laurenz Wiskott, Jean-Marc Fellous, Norbert Krüger, Christoph Der Von Malsburg

Research output: Contribution to journalArticle

2218 Citations (Scopus)

Abstract

(http://www.neuroinformatik.ruhr-uni-bochum.de), when this research was performed. He is now at the Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, San Diego, CA 92186-5800. E-mail: wiskott@cnl.salk.edu. • J.-M. Fellous was with the Computer Science Department, University of Southern California, Los Angeles, CA 90089 when this research was performed. He is now at the Volen Center for Complex Systems, Brandeis University, Waltham, MA 02254-9110. E-mail: fellous@cajal.ccs.brandeis.edu. • N. Krüger and C. von der Malsburg are with the Institute for Neural Computation, Bochum. Christoph von der Malsburg is also with the Computer Science Department, University of Southern California, Los Angeles. Email: {nkrueger, malsburgl@neuroinformatik.ruhr-uni-bochum.de. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.

Original languageEnglish (US)
Pages (from-to)775-779
Number of pages5
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume19
Issue number7
DOIs
StatePublished - 1997
Externally publishedYes

Fingerprint

Graph Matching
Face recognition
Face Recognition
Computer science
Electronic Mail
Graph in graph theory
Wavelet transforms
Data structures
Large scale systems
Computer Science
Face
Gabor Transform
Gabor Wavelet
Wavelet Transform
Positioning
Complex Systems
Data Structures
Person
Vertex of a graph
Neurobiology

Keywords

  • ARPA/ARL FERET database
  • Bochum database
  • Different poses
  • Elastic graph matching, bunch graph
  • Face recognition
  • Gabor wavelets

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Face recognition by elastic bunch graph matching. / Wiskott, Laurenz; Fellous, Jean-Marc; Krüger, Norbert; Von Malsburg, Christoph Der.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, 1997, p. 775-779.

Research output: Contribution to journalArticle

Wiskott, Laurenz ; Fellous, Jean-Marc ; Krüger, Norbert ; Von Malsburg, Christoph Der. / Face recognition by elastic bunch graph matching. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997 ; Vol. 19, No. 7. pp. 775-779.
@article{8994227b0fb749a3a2d47e79b9a676e4,
title = "Face recognition by elastic bunch graph matching",
abstract = "(http://www.neuroinformatik.ruhr-uni-bochum.de), when this research was performed. He is now at the Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, San Diego, CA 92186-5800. E-mail: wiskott@cnl.salk.edu. • J.-M. Fellous was with the Computer Science Department, University of Southern California, Los Angeles, CA 90089 when this research was performed. He is now at the Volen Center for Complex Systems, Brandeis University, Waltham, MA 02254-9110. E-mail: fellous@cajal.ccs.brandeis.edu. • N. Kr{\"u}ger and C. von der Malsburg are with the Institute for Neural Computation, Bochum. Christoph von der Malsburg is also with the Computer Science Department, University of Southern California, Los Angeles. Email: {nkrueger, malsburgl@neuroinformatik.ruhr-uni-bochum.de. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.",
keywords = "ARPA/ARL FERET database, Bochum database, Different poses, Elastic graph matching, bunch graph, Face recognition, Gabor wavelets",
author = "Laurenz Wiskott and Jean-Marc Fellous and Norbert Kr{\"u}ger and {Von Malsburg}, {Christoph Der}",
year = "1997",
doi = "10.1109/34.598235",
language = "English (US)",
volume = "19",
pages = "775--779",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Face recognition by elastic bunch graph matching

AU - Wiskott, Laurenz

AU - Fellous, Jean-Marc

AU - Krüger, Norbert

AU - Von Malsburg, Christoph Der

PY - 1997

Y1 - 1997

N2 - (http://www.neuroinformatik.ruhr-uni-bochum.de), when this research was performed. He is now at the Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, San Diego, CA 92186-5800. E-mail: wiskott@cnl.salk.edu. • J.-M. Fellous was with the Computer Science Department, University of Southern California, Los Angeles, CA 90089 when this research was performed. He is now at the Volen Center for Complex Systems, Brandeis University, Waltham, MA 02254-9110. E-mail: fellous@cajal.ccs.brandeis.edu. • N. Krüger and C. von der Malsburg are with the Institute for Neural Computation, Bochum. Christoph von der Malsburg is also with the Computer Science Department, University of Southern California, Los Angeles. Email: {nkrueger, malsburgl@neuroinformatik.ruhr-uni-bochum.de. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.

AB - (http://www.neuroinformatik.ruhr-uni-bochum.de), when this research was performed. He is now at the Computational Neurobiology Laboratory, The Salk Institute for Biological Studies, San Diego, CA 92186-5800. E-mail: wiskott@cnl.salk.edu. • J.-M. Fellous was with the Computer Science Department, University of Southern California, Los Angeles, CA 90089 when this research was performed. He is now at the Volen Center for Complex Systems, Brandeis University, Waltham, MA 02254-9110. E-mail: fellous@cajal.ccs.brandeis.edu. • N. Krüger and C. von der Malsburg are with the Institute for Neural Computation, Bochum. Christoph von der Malsburg is also with the Computer Science Department, University of Southern California, Los Angeles. Email: {nkrueger, malsburgl@neuroinformatik.ruhr-uni-bochum.de. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one [1] in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.

KW - ARPA/ARL FERET database

KW - Bochum database

KW - Different poses

KW - Elastic graph matching, bunch graph

KW - Face recognition

KW - Gabor wavelets

UR - http://www.scopus.com/inward/record.url?scp=0031187375&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031187375&partnerID=8YFLogxK

U2 - 10.1109/34.598235

DO - 10.1109/34.598235

M3 - Article

AN - SCOPUS:0031187375

VL - 19

SP - 775

EP - 779

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 7

ER -