Advertisement

Collection of Multispectral Biometric Data for Cross-spectral Identification Applications

Chapter

Abstract

The ultimate goal of cross-spectral biometric recognition applications involves matching probe images, captured in one spectral band, against a gallery of images captured in a different band or multiple bands (neither of which is the same band in which the probe images were captured). Both the probe and the gallery images may have been captured in either controlled or uncontrolled environments , i.e., with varying standoff distances, lighting conditions, poses. Development of effective cross-spectral matching algorithms involves, first, the process of collecting a cohort of research sample data under controlled conditions with fixed or varying parameters such as pose, lighting, obstructions, and illumination wavelengths. This chapter details “best practice” collection methodologies developed to compile large-scale datasets of both visible and SWIR face images, as well as gait images and videos. All aspects of data collection , from IRB preparation , through data post-processing , are provided, along with instrumentation layouts for indoor and outdoor live capture setups . Specifications of video and still-imaging cameras used in collections are listed. Controlled collection of 5-pose, ANSI/NIST mugshot images is described, along with multiple SWIR data collections performed both indoors (under controlled illumination) and outdoors. Details of past collections performed at West Virginia University (WVU) to compile multispectral biometric datasets, such as age, gender, and ethnicity of the subject populations, are included. Insight is given on the impact of collection parameters on the general quality of images collected, as well as on how these parameters impact design decisions at the algorithm level. Finally, where applicable, a brief description of how these databases have been used in multispectral biometrics research is included.

Keywords

Face Image Standoff Distance Glass Panel Gait Recognition Vary Lighting Condition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Kalka, N.D., Bourlai, T., Cukic, B., Hornak, L.: Cross-spectral face recognition in heterogeneous environments: a case study on matching visible to short-wave infrared imagery. In: International Joint Conference on Biometrics, 2011Google Scholar
  2. 2.
    Zhu, J.-Y., Zheng, W.-S., Lai, J.-H., Li, S.Z.: Matching NIR face to VIS face using transduction. IEEE Trans. Inf. Forensics Secur. 9(3), 1556–6013 (2014)CrossRefGoogle Scholar
  3. 3.
    Klare, B., Jain, A.K.: Heterogeneous face recognition: matching NIR to visible light images. In: IEEE International Conference on Pattern Recognition, pp. 1513–1516 (2010)Google Scholar
  4. 4.
    Chang, H.: Multispectral imaging for face recognition over varying illumination. Ph.D. dissertation, Department of Electrical Engineering and Computer Science, University of Tennessee, TN (2008)Google Scholar
  5. 5.
    Bourlai, T., Chen, C., Ross, A., Hornak, L.: A study on using mid-wave infrared images for face recognition. SPIE Biometric Technol. Hum. Ident. 9, 83711K (2012)Google Scholar
  6. 6.
    Osia, N., Bourlai, T.: Holistic and partial face recognition in the MWIR band using manual and automatic detection of face-based features. In: IEEE Conference on Technologies for Homeland Security (HST), pp. 273–279 (2012)Google Scholar
  7. 7.
    Mendez, H., San Martin, C., Kittler, J., Plasencia, Y., Garcia-Reyes, E.: Face recognition with LWIR imagery using local binary patterns. In: Advances in Biometrics, pp. 327–336 (2009)Google Scholar
  8. 8.
    Short, N., Hu, S., Gurram, P., Gurton, K., Chan, A.: Improving cross-modal face recognition using polarimetric imaging. Opt. Lett. 40(6) (2015)Google Scholar
  9. 9.
    Gurton, K.P., Yuffa, A.J., Videen, G.W.: Enhanced facial recognition for thermal imagery using polarimetric imaging. Opt. Lett. 39(13), 3857–3859 (2014)Google Scholar
  10. 10.
    Hu, S., Choi, J., Chan, A.L., Schwartz, W.R.: Thermal-to-visible face recognition using partial least squares. J. Opt. Soc. Am. A 32(3), 431–442 (2015)Google Scholar
  11. 11.
    Martin, R.B., Sluch, M., Kafka, K.M., Ice, R., Lemoff, B.E.: Active-SWIR signatures for long-range night/day human detection and identification. In: SPIE, vol. 8734 (2013)Google Scholar
  12. 12.
    Lemoff, B.E., Martin, R.B., Sluch, M., Kafka, K.M., McCormick, W., Ice, R.: Long-range night/day human identification using active-SWIR imaging. In: SPIE: Infrared Technology and Applications, vol. 8704 (2013)Google Scholar
  13. 13.
    Nicolò, F., Schmid, N.A.: Long range cross-spectral face recognition: matching SWIR against visible light images. IEEE: Trans. Inf. Forensics Secur. 7(6), 1717–1726 (2012)Google Scholar
  14. 14.
    Narang, N., Bourlai, T.: Can we match ultraviolet face images against their visible counterparts? In: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultra-spectral Imagery XXI, SPIE (Defense+Security), Baltimore, MD, April 2015Google Scholar
  15. 15.
    Bourlai, T., VonDollen, J., Mavridis, N., Kolanko, C.: Evaluating the efficiency of a nighttime, middle-range infrared sensor for applications in human detection and recognition. In: SPIE, Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXIII, Baltimore, USA, April 2012Google Scholar
  16. 16.
    Chang, H., Yao, Y., Koschan, A., Abidi, B., Abidi, M.: Spectral range selection for face recognition under various illuminations. In: Proceedings of IEEE International Conference on Image Processing, pp. 2756–2759 (2008)Google Scholar
  17. 17.
    Whitelam, C., Bourlai, T.: On designing SWIR to visible face matching algorithms. Intel Technol. J. 18(4), 98–118 (2014)Google Scholar
  18. 18.
  19. 19.
    Dowdall, J., Pavlidis, I., Bebis, G.: Face detection in the near-IR spectrum. Image Vis. Comput. 21, 565–578 (2003)CrossRefGoogle Scholar
  20. 20.
  21. 21.
    Ice, J., Narang, N., Whitelam, C., Kalka, N., Hornak, L., Dawson, J., Bourlai, T.: SWIR imaging for facial image capture through tinted materials. In: Proceedings of SPIE, vol. 8353, p. 83530S (2012)Google Scholar
  22. 22.
    Hansen, M.P., Malchow, D.S.: Overview of SWIR detectors, cameras, and applications. Proc. SPIE 6939, 69390I–69390I-11 (2008)Google Scholar
  23. 23.
    John, J., Zimmermann, L., Merken, P., Borghs, G., Van Hoof, C.A., Nemeth, S.: Extended Backside-illuminated InGaAs on GaAs IR Detectors. Proc. SPIE 4820, 453–459 (2003)CrossRefGoogle Scholar
  24. 24.
    Kalka, N.D., Bourlai, T., Cukic, B., Hornak, L.: Cross-spectral face recognition in heterogeneous environments: a case study of matching visible to short-wave infrared imagery. In: International Joint Conference on Biometrics (IEEE, IAPR), 2011Google Scholar
  25. 25.
    Zuo, J., Nicolo, F., Schmid, N.A., Boothapati, S.: Encoding, matching and score normalization for cross spectral face recognition: matching SWIR versus visible data. In: IEEE Conference on Biometrics Theory, Applications and Systems (BTAS 2012)Google Scholar
  26. 26.
    DeCann, B., Ross, A., Dawson, J.M.: Investigating gait recognition in the short-wave infrared (SWIR) spectrum: dataset and challenges. In: Proceedings of SPIE 8712, Biometric and Surveillance Technology for Human and Activity Identification, X, 87120J, May 31, 2013Google Scholar
  27. 27.
    Pan, Z., Healey, G.E., Prasad, M., Tromberg, B.J.: Hyperspectral face recognition under variable outdoor illumination. In: Proceedings of SPIE International Society of Optical Engineering (OE), Orlando, FL, USA, AprilGoogle Scholar
  28. 28.
    Whitelam, C., Bourlai, T.: Accurate eye localization in the short waved infrared spectrum through summation range filters. J. Comput. Vis. Image Underst. (CVIU) 139, 59–72 (2015)Google Scholar
  29. 29.
    Whitelam, C., Bourlai, T.: On designing an unconstrained tri-band pupil detection system for human identification. J. Mach. Vis. Appl. 1–19 (2015)Google Scholar
  30. 30.
    Narang, N., Bourlai, T.: Face recognition in the SWIR band when using single sensor multi-wavelength imaging systems. J Image Vis. Comput. 33, 26–43 (2015)CrossRefGoogle Scholar
  31. 31.
    Kang, J., Borkar, A., Yeung, A., Nong, N., Smith, M., Hayes, M.: Short wavelength infrared face recognition for personalization. In: Proceedings of the IEEE International Conference on Image Processing (ICIP’06), pp. 2757–2760, October 2006, Atlanta, GAGoogle Scholar
  32. 32.
    Ngo, H.T., Ives, R.W., Matey, J.R., Dormo, J., Rhoads, M., Choi, D.: Design and implementation of a multispectral iris capture system. In: Signals, Systems, and Computers, 2009 Conference Record of the Forty-Third Asilomar Conference on, pp. 380–384, IEEE Piscataway, NJ (2009)Google Scholar
  33. 33.
    Steiner, H., Sporrer, S., Kolb, A., Jung, N.: Design of an active multispectral SWIR camera system for skin detection and face verification. J. Sens., Article ID 456368 (2015)Google Scholar
  34. 34.
    Pavlidis, I., Symosek, P.: The imaging issue in an automatic face/disguise detection system. In: Proceedings of IEEE Workshop Computer Vision Beyond the Visible Spectrum: Methods and Applications, pp. 15–24 (2000)Google Scholar
  35. 35.
    Jacquez, J.A., Huss, J., Mckeehan, W., Dimitroff, J.M., Kuppenheim, H.F.: Spectral reflectance of human skin in the region 0.7–2.6μm. J. Appl. Physiol. 8(3), 297–299 (1955)Google Scholar
  36. 36.
    Bertozzi, M., Fedriga, R., Miron, A., Reverchon, J.-L.: Pedestrian detection in poor visibility conditions: would SWIR help? In: Petrosino, A. (ed.) Image Analysis and Processing—ICIAP 2013, vol. 8157 of Lecture Notes in Computer Science, pp. 229–238. Springer, Berlin (2013)Google Scholar
  37. 37.
    Lemoff, B.E., Martin, R.B., Sluch, M., Kafka, K.M., Dolby, A., Ice, R.: Automated, long-range, night/day, active-SWIR face recognition system. In: 40th Infrared Technology and Applications, vol. 9070 of Proceedings of SPIE, pp. 90703I-1–90703I-10, Baltimore, Md, USA, June 2014Google Scholar
  38. 38.
    Zhou, Q., Xu, Z., Liao, S., Wei, J.: Morphological modified global thresholding and 8 adjacent neighborhood labeling for SWIR image mosaic. In: International Conference on Optoelectronics and Image Processing (ICOIP), 2010, vol. 2, pp. 19, 23, 11–12 Nov 2010Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Lane Department of Computer Science and Electrical Engineering, Statler College of Engineering and Mineral ResourcesWest Virginia UniversityMorgantownUSA

Personalised recommendations