Robust face detection and tracking for real-life applications

Hyeran Byun, Byoungchul Ko

Research output: Contribution to journalLetter

10 Citations (Scopus)

Abstract

In this paper, we propose a new face detection and tracking algorithm for real-life telecommunication applications, such as video conferencing, cellular phone and PDA. We combine template-based face detection and tracking method with color information to track a face regardless of various lighting conditions and complex backgrounds as well as the race. Based on our experiments, we generate robust face templates from wavelet-transformed lowpass and two highpass subimages at the second level low-resolution. However, since template matching is generally sensitive to the change of illumination conditions, we propose a new type of preprocessing method. Tracking method is applied to reduce the computation time and predict precise face candidate region even though the movement is not uniform. Facial components are also detected using k-means clustering and their geometrical properties. Finally, from the relative distance of two eyes, we verify the real face and estimate the size of facial ellipse. To validate face detection and tracking performance of our algorithm, we test our method using six different video categories of QCIF size which are recorded in dynamic environments.

Original languageEnglish
Pages (from-to)1035-1055
Number of pages21
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume17
Issue number6
DOIs
Publication statusPublished - 2003 Sep 1

Fingerprint

Face recognition
Lighting
Video conferencing
Template matching
Personal digital assistants
Telecommunication
Color
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{c9d88328caec49d99a855e25f1de27e4,
title = "Robust face detection and tracking for real-life applications",
abstract = "In this paper, we propose a new face detection and tracking algorithm for real-life telecommunication applications, such as video conferencing, cellular phone and PDA. We combine template-based face detection and tracking method with color information to track a face regardless of various lighting conditions and complex backgrounds as well as the race. Based on our experiments, we generate robust face templates from wavelet-transformed lowpass and two highpass subimages at the second level low-resolution. However, since template matching is generally sensitive to the change of illumination conditions, we propose a new type of preprocessing method. Tracking method is applied to reduce the computation time and predict precise face candidate region even though the movement is not uniform. Facial components are also detected using k-means clustering and their geometrical properties. Finally, from the relative distance of two eyes, we verify the real face and estimate the size of facial ellipse. To validate face detection and tracking performance of our algorithm, we test our method using six different video categories of QCIF size which are recorded in dynamic environments.",
author = "Hyeran Byun and Byoungchul Ko",
year = "2003",
month = "9",
day = "1",
doi = "10.1142/S0218001403002721",
language = "English",
volume = "17",
pages = "1035--1055",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

Robust face detection and tracking for real-life applications. / Byun, Hyeran; Ko, Byoungchul.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 17, No. 6, 01.09.2003, p. 1035-1055.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Robust face detection and tracking for real-life applications

AU - Byun, Hyeran

AU - Ko, Byoungchul

PY - 2003/9/1

Y1 - 2003/9/1

N2 - In this paper, we propose a new face detection and tracking algorithm for real-life telecommunication applications, such as video conferencing, cellular phone and PDA. We combine template-based face detection and tracking method with color information to track a face regardless of various lighting conditions and complex backgrounds as well as the race. Based on our experiments, we generate robust face templates from wavelet-transformed lowpass and two highpass subimages at the second level low-resolution. However, since template matching is generally sensitive to the change of illumination conditions, we propose a new type of preprocessing method. Tracking method is applied to reduce the computation time and predict precise face candidate region even though the movement is not uniform. Facial components are also detected using k-means clustering and their geometrical properties. Finally, from the relative distance of two eyes, we verify the real face and estimate the size of facial ellipse. To validate face detection and tracking performance of our algorithm, we test our method using six different video categories of QCIF size which are recorded in dynamic environments.

AB - In this paper, we propose a new face detection and tracking algorithm for real-life telecommunication applications, such as video conferencing, cellular phone and PDA. We combine template-based face detection and tracking method with color information to track a face regardless of various lighting conditions and complex backgrounds as well as the race. Based on our experiments, we generate robust face templates from wavelet-transformed lowpass and two highpass subimages at the second level low-resolution. However, since template matching is generally sensitive to the change of illumination conditions, we propose a new type of preprocessing method. Tracking method is applied to reduce the computation time and predict precise face candidate region even though the movement is not uniform. Facial components are also detected using k-means clustering and their geometrical properties. Finally, from the relative distance of two eyes, we verify the real face and estimate the size of facial ellipse. To validate face detection and tracking performance of our algorithm, we test our method using six different video categories of QCIF size which are recorded in dynamic environments.

UR - http://www.scopus.com/inward/record.url?scp=0142022851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142022851&partnerID=8YFLogxK

U2 - 10.1142/S0218001403002721

DO - 10.1142/S0218001403002721

M3 - Letter

AN - SCOPUS:0142022851

VL - 17

SP - 1035

EP - 1055

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 6

ER -