TY - GEN
T1 - Implementation of 3-D linear phase coefficient composite filters
AU - Woon, Delicia
AU - Hassebrook, Laurence G.
AU - Lau, Daniel L.
AU - Wang, Zhen Zhou
PY - 2006
Y1 - 2006
N2 - The use of 3-Dimensional information in face recognition requires pose estimation. We present the use of 3-Dimensional composite correlation filter to obtain pose estimation without the need for feature identification. Composite correlation filter research has been vigorously pursued in the last three decades due to their applications in many areas, but mainly in distortion-invariant pattern recognition. While most of this research is in two-dimensional space, we have extended our study of composite filters to three-dimensions, specifically emphasizing Linear Phase Coefficient Composite Filter (LPCCF). Unlike previous approaches to composite filter design, this method considers the filter design and the training set selection simultaneously. In this research, we demonstrate the potential of implementing LPCCF in head pose estimation. We introduce the utilization of LPCCF in the application of head pose recovery through full correlation using a set of 3-D voxel maps instead of the typical 2-D pixel images/silhouettes. Unlike some existing approaches to pose estimation, we are able to acquire 3-D head pose without locating salient features of a subject. In theory, the correlation phase response contains information about the angle of head rotation of the subject. Pose estimation experiments are conducted for two degrees of freedom in rotation, that is, yaw and pitch angles. The results obtained are very much inline with our theoretical hypothesis on head orientation estimation.
AB - The use of 3-Dimensional information in face recognition requires pose estimation. We present the use of 3-Dimensional composite correlation filter to obtain pose estimation without the need for feature identification. Composite correlation filter research has been vigorously pursued in the last three decades due to their applications in many areas, but mainly in distortion-invariant pattern recognition. While most of this research is in two-dimensional space, we have extended our study of composite filters to three-dimensions, specifically emphasizing Linear Phase Coefficient Composite Filter (LPCCF). Unlike previous approaches to composite filter design, this method considers the filter design and the training set selection simultaneously. In this research, we demonstrate the potential of implementing LPCCF in head pose estimation. We introduce the utilization of LPCCF in the application of head pose recovery through full correlation using a set of 3-D voxel maps instead of the typical 2-D pixel images/silhouettes. Unlike some existing approaches to pose estimation, we are able to acquire 3-D head pose without locating salient features of a subject. In theory, the correlation phase response contains information about the angle of head rotation of the subject. Pose estimation experiments are conducted for two degrees of freedom in rotation, that is, yaw and pitch angles. The results obtained are very much inline with our theoretical hypothesis on head orientation estimation.
KW - 3-D
KW - Composite Filter
KW - Face Recognition
KW - Head Pose Estimation
KW - LPCCF
KW - VIPM
UR - http://www.scopus.com/inward/record.url?scp=33748552419&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33748552419&partnerID=8YFLogxK
U2 - 10.1117/12.666392
DO - 10.1117/12.666392
M3 - Conference contribution
AN - SCOPUS:33748552419
SN - 081946290X
SN - 9780819462909
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Automatic Target Recognition XVI
T2 - Automatic Target Recognition XVI
Y2 - 18 April 2006 through 19 April 2006
ER -