SWIR imaging for facial image capture through tinted materials

The use of short wave infrared (SWIR) imaging and illumination technology is at the forefront of system development for military and law enforcement in both night and daytime operational scenarios1 2 3 4 . Along with enabling nighttime operations, a secondary benefit of SWIR imaging is that it offers the possibility to capture images through tinted materials, such as tinted architectural or automotive glass and sunglass lenses5. The use of SWIR technology introduces challenges to facial recognition when comparing cross-spectrally from a visible gallery to images captured in the SWIR6. The challenges of SWIR facial recognition are further compounded by the presence of tinted materials in the imaging path due to varying material types, lighting conditions, and viewing angle. The paper discusses material and optical characterization efforts undertaken to understand the effects of temperature, interior and exterior light sources, and viewing angle on the quality of facial images captured through tinted materials. Temperature vs. spectrum curves are shown for tinted architectural, automotive, and sunglass materials over the range of -10 to 55C. The results of imaging under various permutations of interior and exterior lighting, along with viewing angle, are used to evaluate the efficacy of eye detection for cross-spectral facial recognition under these conditions.

[1]  Raf Vandersmissen Night-vision camera combines thermal and low-light-level images Image Capturing and Processing , 2008 .

[2]  Douglas S. Malchow,et al.  Overview of SWIR detectors, cameras, and applications , 2008, SPIE Defense + Commercial Sensing.

[3]  Arun Ross,et al.  Exploring multispectral iris recognition beyond 900nm , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[4]  Patrick Merken,et al.  Extended backside-illuminated InGaAs on GaAs IR detectors , 2003, SPIE Optics + Photonics.

[5]  Natalia A. Schmid,et al.  A Method for Robust Multispectral Face Recognition , 2011, ICIAR.

[6]  Shengcai Liao,et al.  Illumination Invariant Face Recognition Using Near-Infrared Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Mongi A. Abidi,et al.  Spectral range selection for face recognition under various illuminations , 2008, 2008 15th IEEE International Conference on Image Processing.

[8]  Dong Yi,et al.  Face Matching Between Near Infrared and Visible Light Images , 2007, ICB.

[9]  Arun Ross,et al.  Ascertaining Human Identity in Night Environments , 2011 .

[10]  Arun Ross,et al.  Cross-Spectral Face Verification in the Short Wave Infrared (SWIR) Band , 2010, 2010 20th International Conference on Pattern Recognition.

[11]  Ioannis Pavlidis,et al.  Infrared and visible image fusion for face recognition , 2004, SPIE Defense + Commercial Sensing.

[12]  Bojan Cukic,et al.  Cross-spectral face recognition in heterogeneous environments: A case study on matching visible to short-wave infrared imagery , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[13]  S. Thennadil,et al.  Optical properties of human skin in the near infrared wavelength range of 1000 to 2200 nm. , 2001, Journal of biomedical optics.

[14]  Thirimachos Bourlai,et al.  Multispectral Eye Detection: A Preliminary Study , 2010, 2010 20th International Conference on Pattern Recognition.

[15]  Seong G. Kong,et al.  Recent advances in visual and infrared face recognition - a review , 2005, Comput. Vis. Image Underst..