Fast 3D NIR systems for facial measurement and lip-reading

Structured-light projection is a well-established optical method for the non-destructive contactless three-dimensional (3D) measurement of object surfaces. In particular, there is a great demand for accurate and fast 3D scans of human faces or facial regions of interest in medicine, safety, face modeling, games, virtual life, or entertainment. New developments of facial expression detection and machine lip-reading can be used for communication tasks, future machine control, or human-machine interactions. In such cases, 3D information may offer more detailed information than 2D images which can help to increase the power of current facial analysis algorithms. In this contribution, we present new 3D sensor technologies based on three different methods of near-infrared projection technologies in combination with a stereo vision setup of two cameras. We explain the optical principles of an NIR GOBO projector, an array projector and a modified multi-aperture projection method and compare their performance parameters to each other. Further, we show some experimental measurement results of applications where we realized fast, accurate, and irritation-free measurements of human faces.

[1]  Andreas Tünnermann,et al.  Theoretical considerations on aperiodic sinusoidal fringes in comparison to phase-shifted sinusoidal fringes for high-speed three-dimensional shape measurement. , 2015, Applied optics.

[2]  H. McGurk,et al.  Hearing lips and seeing voices , 1976, Nature.

[3]  Andreas Tünnermann,et al.  Ultraslim fixed pattern projectors with inherent homogenization of illumination. , 2012, Applied optics.

[4]  Peter Schreiber,et al.  Array projection optics: multi-channel design for ultra slim projectors , 2010, Photonics Europe.

[5]  Jing Li,et al.  Data fusion-based real-time hand gesture recognition with Kinect V2 , 2016, 2016 9th International Conference on Human System Interactions (HSI).

[6]  YoungSteve,et al.  The application of hidden Markov models in speech recognition , 2007 .

[7]  A. Tünnermann,et al.  High-speed three-dimensional shape measurement using GOBO projection , 2016 .

[8]  Martin Schaffer,et al.  High-speed three-dimensional shape measurements of objects with laser speckles and acousto-optical deflection. , 2011, Optics letters.

[9]  Luc Van Gool,et al.  Combining RGB and ToF cameras for real-time 3D hand gesture interaction , 2011, WACV.

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

[11]  Léon J. M. Rothkrantz,et al.  Automatic Visual Speech Recognition , 2012 .

[12]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Peter Kühmstedt,et al.  Array projection of aperiodic sinusoidal fringes for high-speed three-dimensional shape measurement , 2014 .

[14]  Davis E. King,et al.  Dlib-ml: A Machine Learning Toolkit , 2009, J. Mach. Learn. Res..

[15]  Mark J. F. Gales,et al.  The Application of Hidden Markov Models in Speech Recognition , 2007, Found. Trends Signal Process..

[16]  Jason Geng,et al.  Structured-light 3D surface imaging: a tutorial , 2011 .

[17]  Joaquim Salvi,et al.  A state of the art in structured light patterns for surface profilometry , 2010, Pattern Recognit..