Pattern-based Face Localization and Online Projector Parameterization for Multi-Camera 3D Scanning

3D face modeling is a very important and challenging task in computer vision especially in the presence of an expression variation. It plays an important role in a wide range of applications including facial animation, human-computer interaction and surgery. Current 3D face imaging solutions are often based on structured light camera/projector systems to overcome the relatively uniform appearance of skin. This paper proposes a space-time scheme for 3D face scanning, employing three calibrated cameras coupled with a non calibrated projector device. The proposed solution is a hybrid stereovision and phase-shifting approach, using two π-shifted sinusoid patterns and a texture image. It involves a pattern-based face localization approach and an online projector parameterization. The experimental results further validated the effectiveness of the proposed approach.

[1]  Song Zhang,et al.  High-resolution, real-time three-dimensional shape measurement , 2006 .

[2]  Faouzi Ghorbel,et al.  Pattern Analysis for an Automatic and Low-Cost 3D Face Acquisition Technique , 2009, ACIVS.

[3]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Sebastian Thrun,et al.  LidarBoost: Depth superresolution for ToF 3D shape scanning , 2009, CVPR.

[5]  Yunhong Wang,et al.  3D Face Recognition Based on Local Shape Patterns and Sparse Representation Classifier , 2011, MMM.

[6]  Faouzi Ghorbel,et al.  Multi-camera 3D Scanning with a Non-rigid and Space-Time Depth Super-Resolution Capability , 2011, CAIP.

[7]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Nina Amenta,et al.  Laser Scanner Super-resolution , 2006, PBG@SIGGRAPH.

[9]  Song Zhang.  Recent progresses on real-time 3D shape measurement using digital fringe projection techniques , 2010 .

[10]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[11]  Song Zhang,et al.  Absolute phase-assisted three-dimensional data registration for a dual-camera structured light system. , 2008, Applied optics.

[12]  Miguel Á. Carreira-Perpiñán,et al.  Non-rigid point set registration: Coherent Point Drift , 2006, NIPS.

[13]  Faouzi Ghorbel,et al.  A Space-Time Depth Super-Resolution Scheme for 3D Face Scanning , 2011, ACIVS.

[14]  Michael Elad,et al.  Fast and robust multiframe super resolution , 2004, IEEE Transactions on Image Processing.

[15]  Li Zhang,et al.  Rapid shape acquisition using color structured light and multi-pass dynamic programming , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.