Fusion of appearance and depth information for face recognition

Jian Gang Wang, Kar Ann Toh, Ronda Venkateswarlu

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

In this paper, an investigation is carried out regarding combination of 3D and 2D information for face recognition. A two-stage method, PCA and a Reduced Multivariate Polynomial Model (RMPM), is developed to fuse the appearance and depth information of face images in feature level where simplicity (number of polynomial coefficients increases linearly with model-order and input-dimension, i.e. no dimension explosion as in the case of full multivariate polynomials) and ease of use (can be easily formulated into recursive learning fashion) are major concerns. To cater for fast on-line registration capability when a new user arrives, the learning is formulated into recursive form. The improvement of the face recognition rate using this combination is quantified. The recognition rate by the combination is better than either appearance alone or depth alone. The performance of the algorithm is verified on both XM2VTS database and a real-time stereo vision system, showing that it is able to detect, track and recognize a person walking towards a stereo camera within reasonable time.

Original languageEnglish
Pages (from-to)919-928
Number of pages10
JournalLecture Notes in Computer Science
Volume3546
Publication statusPublished - 2005 Oct 17
Event5th International Conference on Audio - and Video-Based Biometric Person Authentication, AVBPA 2005 - Hilton Rye Town, NY, United States
Duration: 2005 Jul 202005 Jul 22

Fingerprint

Face recognition
Face Recognition
Fusion
Fusion reactions
Multivariate Polynomials
Polynomials
Stereo vision
Electric fuses
Explosions
Polynomial Model
Stereo Vision
Cameras
Multivariate Models
Vision System
Explosion
Registration
Simplicity
Person
Linearly
Camera

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Wang, Jian Gang ; Toh, Kar Ann ; Venkateswarlu, Ronda. / Fusion of appearance and depth information for face recognition. In: Lecture Notes in Computer Science. 2005 ; Vol. 3546. pp. 919-928.
@article{4e813e6533924b778aec7ca77659f6e6,
title = "Fusion of appearance and depth information for face recognition",
abstract = "In this paper, an investigation is carried out regarding combination of 3D and 2D information for face recognition. A two-stage method, PCA and a Reduced Multivariate Polynomial Model (RMPM), is developed to fuse the appearance and depth information of face images in feature level where simplicity (number of polynomial coefficients increases linearly with model-order and input-dimension, i.e. no dimension explosion as in the case of full multivariate polynomials) and ease of use (can be easily formulated into recursive learning fashion) are major concerns. To cater for fast on-line registration capability when a new user arrives, the learning is formulated into recursive form. The improvement of the face recognition rate using this combination is quantified. The recognition rate by the combination is better than either appearance alone or depth alone. The performance of the algorithm is verified on both XM2VTS database and a real-time stereo vision system, showing that it is able to detect, track and recognize a person walking towards a stereo camera within reasonable time.",
author = "Wang, {Jian Gang} and Toh, {Kar Ann} and Ronda Venkateswarlu",
year = "2005",
month = "10",
day = "17",
language = "English",
volume = "3546",
pages = "919--928",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",

}

Fusion of appearance and depth information for face recognition. / Wang, Jian Gang; Toh, Kar Ann; Venkateswarlu, Ronda.

In: Lecture Notes in Computer Science, Vol. 3546, 17.10.2005, p. 919-928.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Fusion of appearance and depth information for face recognition

AU - Wang, Jian Gang

AU - Toh, Kar Ann

AU - Venkateswarlu, Ronda

PY - 2005/10/17

Y1 - 2005/10/17

N2 - In this paper, an investigation is carried out regarding combination of 3D and 2D information for face recognition. A two-stage method, PCA and a Reduced Multivariate Polynomial Model (RMPM), is developed to fuse the appearance and depth information of face images in feature level where simplicity (number of polynomial coefficients increases linearly with model-order and input-dimension, i.e. no dimension explosion as in the case of full multivariate polynomials) and ease of use (can be easily formulated into recursive learning fashion) are major concerns. To cater for fast on-line registration capability when a new user arrives, the learning is formulated into recursive form. The improvement of the face recognition rate using this combination is quantified. The recognition rate by the combination is better than either appearance alone or depth alone. The performance of the algorithm is verified on both XM2VTS database and a real-time stereo vision system, showing that it is able to detect, track and recognize a person walking towards a stereo camera within reasonable time.

AB - In this paper, an investigation is carried out regarding combination of 3D and 2D information for face recognition. A two-stage method, PCA and a Reduced Multivariate Polynomial Model (RMPM), is developed to fuse the appearance and depth information of face images in feature level where simplicity (number of polynomial coefficients increases linearly with model-order and input-dimension, i.e. no dimension explosion as in the case of full multivariate polynomials) and ease of use (can be easily formulated into recursive learning fashion) are major concerns. To cater for fast on-line registration capability when a new user arrives, the learning is formulated into recursive form. The improvement of the face recognition rate using this combination is quantified. The recognition rate by the combination is better than either appearance alone or depth alone. The performance of the algorithm is verified on both XM2VTS database and a real-time stereo vision system, showing that it is able to detect, track and recognize a person walking towards a stereo camera within reasonable time.

UR - http://www.scopus.com/inward/record.url?scp=26444515950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444515950&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:26444515950

VL - 3546

SP - 919

EP - 928

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -