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 language | English |
---|---|
Pages (from-to) | 1035-1055 |
Number of pages | 21 |
Journal | International Journal of Pattern Recognition and Artificial Intelligence |
Volume | 17 |
Issue number | 6 |
DOIs | |
Publication status | Published - 2003 Sep 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
- Artificial Intelligence
Cite this
}
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 journal › Letter
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 -