TY - GEN
T1 - Detection of human face motion and its application to avatar movement
AU - Jing Wen Zhou, A.
AU - Young-One Cho, B.
AU - Jin-Woo Jung, C.
PY - 2012
Y1 - 2012
N2 - Face pose tracking, a basic research topic in the field of computer vision and intelligent human computer interaction, is becoming more and more attractive recently. The main objective of face pose tracking is estimating the 3D pose parameters from an image sequence with human faces. The technology of face pose tracking can be widely used in face recognition, expression recognition, gesture understanding, video conference, intelligent surveillance, fatigue detection, virtual reality, game and entertainments. This paper presents a detection algorithm of human face motion. The guideline is capturing human face motion video stream through a common web camera and processing with OpenCV library function according to the following process: First the region of human face in the video stream is detected. Then the region of human eyes and nose is determined and localized. At last a 3-dimensional human face model is built to simulate human face movement by analyzing large amount of data and image frame.
AB - Face pose tracking, a basic research topic in the field of computer vision and intelligent human computer interaction, is becoming more and more attractive recently. The main objective of face pose tracking is estimating the 3D pose parameters from an image sequence with human faces. The technology of face pose tracking can be widely used in face recognition, expression recognition, gesture understanding, video conference, intelligent surveillance, fatigue detection, virtual reality, game and entertainments. This paper presents a detection algorithm of human face motion. The guideline is capturing human face motion video stream through a common web camera and processing with OpenCV library function according to the following process: First the region of human face in the video stream is detected. Then the region of human eyes and nose is determined and localized. At last a 3-dimensional human face model is built to simulate human face movement by analyzing large amount of data and image frame.
KW - 3-Dimensional face model
KW - Face detection
KW - Face pose estimation
UR - http://www.scopus.com/inward/record.url?scp=84873322741&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84873322741
SN - 9781601322258
T3 - Proceedings of the 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
SP - 598
EP - 602
BT - Proceedings of the 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
T2 - 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
Y2 - 16 July 2012 through 19 July 2012
ER -