Facial Orientation and Eye-Gaze Detection Based on Real-Time 3D Facial Imaging By Using Correlation Image Sensor

3D facial orientation and eye-gaze detection is one hot area in human-machine interaction and application, it is also a challenging field in computer vision, pattern recognition and image sensing. We designed a real-time 3D facial orientation and eye-gaze detection system based on 3D real-time facial imaging system by using three-phase correlation image sensor. Based on the normal vector map and intensity image obtained by our imaging system simultaneously, the differential geometry theory is employed to find the key points of face image, according to these key points and curvature feature of face, the important eye area could be segmented from the face image. The optical flow algorithm originally presented by Bruce D. Lucas and Takeo Kanade is implemented to get the detection result. The experiments show that the performance for our test is satisfying

[1]  Shigeru Ando,et al.  Surface orientation imager using three-phase amplitude-modulated illumination and correlation image sensor , 2003, IS&T/SPIE Electronic Imaging.

[2]  Jian-Gang Wang,et al.  Eye gaze estimation from a single image of one eye , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[3]  Raghu Machiraju,et al.  Model-based 3D face capture with shape-from-silhouettes , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[4]  Shigeru Ando,et al.  Consistent Gradient Operators , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Arne John Glenstrup,et al.  Eye Controlled Media: Present and Future State , 1995 .

[6]  Surendra Ranganath,et al.  Pose-invariant face recognition using a 3D deformable model , 2003, Pattern Recognit..

[7]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[8]  Antonio García Dopico,et al.  A Precise Eye-Gaze Detection and Tracking System , 2003, WSCG.

[9]  Mubarak Shah,et al.  Monitoring head/eye motion for driver alertness with one camera , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[10]  S. Ando,et al.  Correlation image sensor: two-dimensional matched detection of amplitude-modulated light , 2003 .

[11]  Qiang Ji,et al.  Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance , 2002, Real Time Imaging.