Multispectral Face Imaging and Analysis

  • Andreas KoschanEmail author
  • Yi Yao
  • Hong Chang
  • Mongi Abidi


This chapter addresses the advantages of using multispectral narrow-band images for face recognition, as opposed to conventional broad-band images obtained by color or monochrome cameras. Narrow-band images are by definition taken over a very small range of wavelengths, while broad-band images average the information obtained over a wide range of wavelengths. There are two primary reasons for employing multispectral imaging for face recognition.


Face Recognition Spectral Band Multispectral Image Tunable Filter Band Selection 
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.



This work was supported in part by the DOE University Research Program in Robotics under grant DOE-DEFG02-86NE37968 and NSF-CITeR grant 01-598B-UT.


  1. 1.
    Bajcsy, P., Groves, P.: Methodology for hyperspectral band selection. Photogramm. Eng. Remote Sens. 70, 793–802 (2004) Google Scholar
  2. 2.
    Bassett, E.M., Shen, S.S.: Information theory-based band selection for multispectral systems. In: SPIE, vol. 3118, pp. 28–35 (1997) CrossRefGoogle Scholar
  3. 3.
    Bozdogan, H.: Akaike’s information criterion and recent developments in information complexity. J. Math. Psychol. 44, 62–91 (2000) MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Bruce, L., Koger, C., Li, J.: Dimensionality reduction of hyperspectral data using discrete wavelet transform extraction. IEEE Trans. Geosci. Remote Sens. 40(10), 2331–2338 (2002) CrossRefGoogle Scholar
  5. 5.
    Brusco, M.J.: An enhanced branch-and-bound algorithm for a partitioning problem. Br. J. Math. Stat. Psychol. 56, 83–92 (2003) MathSciNetCrossRefGoogle Scholar
  6. 6.
    Bruzzone, L., Roli, F., Serpico, S.B.: An extension of the Jeffreys–Matusita distance to multiclass cases for feature selection. IEEE Trans. Geosci. Remote Sens. 33(6), 1318–1321 (1995) CrossRefGoogle Scholar
  7. 7.
    Chang, C.I., Du, Q., Sun, T.S., Althouse, M.L.G.: A joint band prioritization and band decorrelation approach to band selection for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 37(6), 2631–2641 (1999) CrossRefGoogle Scholar
  8. 8.
    Chang, H., Yao, Y., Koschan, A., Abidi, B., Abidi, M.: Spectral range selection for face recognition under various illuminations. In: IEEE Int’l Conf. on Image Processing, San Diego, CA, October 2008 Google Scholar
  9. 9.
    Chang, H., Yao, Y., Koschan, A., Abidi, B., Abidi, M.: Improving face recognition via narrow-band spectral range selection using Jeffrey divergence. IEEE Trans. Inf. Forensics Secur. 4(1), 111–122 (2009) CrossRefGoogle Scholar
  10. 10.
    Chang, H., Koschan, A., Abidi, B., Abidi, M.: Fusing continuous spectral images for face recognition under indoor and outdoor illuminants. Mach. Vis. Appl. 21, 201–215 (2010) CrossRefGoogle Scholar
  11. 11.
    Du, H., Qi, H., Wang, X., Ramanath, R., Snyder, W.E.: Band selection using independent component analysis for hyperspectral image processing. In: Applied Imagery Pattern Recognition Workshop, pp. 93–98 (2003) Google Scholar
  12. 12.
    El-ghazawi, T., Kaewpijit, S., Le Moigne, J.: Parallel and adaptive reduction of hyperspectral data to intrinsic dimensionality. In: IEEE Int’l Conf. on Cluster Computing (2001) Google Scholar
  13. 13.
    Finlayson, G.D., Morovic, P.M., Hordley, S.D.: Using the spectracube for multispectral imaging. In: 2nd Conference on Color in Imaging, Vision and Graphics, pp. 268–274 (2004) Google Scholar
  14. 14.
    Gat, N.: Imaging spectroscopy using tunable filters: a review. In: SPIE, vol. 4056, pp. 50–64 (2000) CrossRefGoogle Scholar
  15. 15.
    Gonzalez, R., Woods, R.: Digital Image Processing. Prentice Hall, New York (2004) Google Scholar
  16. 16.
    Gottlieb, M.S.: Acousto-optic tunable filters. In: Design and Fabrication of Acousto-Optic Devices, pp. 197–284. Marcel Dekker, New York (1994) Google Scholar
  17. 17.
    Hardeberg, J.Y., Schmitt, F., Brettel, H.: Multispectral image capture using a liquid crystal tunable filters. Opt. Eng. 41(10), 2532–2548 (2002) CrossRefGoogle Scholar
  18. 18.
    Healey, G., Slater, D.: Invariant recognition in hyperspectral images. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 438–443, Ft. Collins, CO, June 1999 Google Scholar
  19. 19.
  20. 20.
    Imai, F.H., Berns, R.S.: High-resolution multispectral image archives: a hybrid approach. In: IS&T SID Sixth Color Imaging Conf., pp. 185–189 (1998) Google Scholar
  21. 21.
    Imai, F.H., Rosen, M.R., Berns, R.S.: Multi-spectral imaging of a van Gogh’s self-portrait at the National Gallery of Art, Washington, D.C. In: IS&T PICS, pp. 185–189 (2001) Google Scholar
  22. 22.
    Jeffreys, H.: An invariant form for the prior probability in estimation problems. Proc. R. Soc. 186, 453–461 (1946) MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Jiang, L., Mann, B., Mathur, A.: Wavelet transform for dimensionality reduction in hyperspectral linear unmixing. In: IEEE Int’l Geoscience and Remote Sensing Symposium, vol. 6, pp. 3513–3515 (2002) Google Scholar
  24. 24.
    Jimenez, L.O., Landgrebe, D.A.: Supervised classification in high dimensional space: geometrical statistical and asymptotical properties of multivariate data. IEEE Trans. Syst. Man Cybern. 28(1), 39–54 (1998) CrossRefGoogle Scholar
  25. 25.
    Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97, 273–324 (1997) zbMATHCrossRefGoogle Scholar
  26. 26.
    Koller, D., Sahami, M.: Towards optimal feature selection. In: Int’l Conf. on Machine Learning, pp. 284–292, Bari, Italy, July 1996 Google Scholar
  27. 27.
    Korycinski, D., Crawford, M.M., Barnes, J.W.: Adaptive feature selection for hyperspectral data analysis using a binary hierarchical classifier and tabu search. In: Int’l Geoscience and Remote Sensing Symposium, pp. 297–299 (2003) Google Scholar
  28. 28.
    Kudo, M., Sklansky, J.: Comparison of algorithms that select features for pattern classifiers. Pattern Recognit. 33(1), 25–41 (2000) CrossRefGoogle Scholar
  29. 29.
    Kuman, S., Ghosh, J., Crawford, M.M.: Best basis feature extraction algorithms for classification of hyperspectral data. IEEE Trans. Geosci. Remote Sens. 39(7), 1368–1379 (2001) CrossRefGoogle Scholar
  30. 30.
    Lennon, M., Mercier, G., Mouchot, M., Hubert-Moy, L.: Independent component analysis as a tool for the dimensionality reduction and the representation of hyperspectral image. In: IEEE Int’l Geoscience and Remote Sensing Symposium, vol. 6, pp. 2893–2895 (2001) Google Scholar
  31. 31.
    Liu, C., Wechsler, H.: A unified Bayesian framework for face recognition. In: IEEE Int’l Conf. on Image Processing, pp. 151–155, Chicago, IL, October 1998 Google Scholar
  32. 32.
    Mugdadi, A.R., Munthali, E.: Relative efficiency in kernel estimation of the distribution function. J. Stat. Res. 37(2), 203–218 (2003) MathSciNetGoogle Scholar
  33. 33.
    Ohta, N., Takahashi, K., Urabe, H., Miyagawa, T.: Image simulation by use of a laser color printer. O plus E 22, 57–64 (1981) Google Scholar
  34. 34.
    Pan, Z., Healey, G., Prasad, M., Tromber, B.: Face recognition in hyperspectral images. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1552–1560 (2003) CrossRefGoogle Scholar
  35. 35.
    Pan, Z., Healey, G., Prasad, M., Tromberg, B.: Hyperspectral face recognition under variable outdoor illumination. In: SPIE, vol. 5425, pp. 520–529 (2004) CrossRefGoogle Scholar
  36. 36.
    Parkkinen, J., Oja, E., Jaaskelainen, T.: Color analysis by learning subspaces and optical processing. In: Int’l Conf. on Neural Networks (1988) Google Scholar
  37. 37.
    Parzen, E.: On estimation of a probability density function and model. Ann. Math. Stat. 33(3), 1065–1076 (1962) MathSciNetzbMATHCrossRefGoogle Scholar
  38. 38.
    Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005) CrossRefGoogle Scholar
  39. 39.
    Poger, S., Angelopoulou, E.: Selecting components for building multispectral sensors. In: IEEE CVPR Technical Sketches (2001) Google Scholar
  40. 40.
    Rosen, M., Jiang, X.: Lippmann2000: a spectral image database under construction. In: Int’l Symposium on Multispectral Imaging and Color Reproduction for Digital Archives, pp. 117–122 (1999) Google Scholar
  41. 41.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000) CrossRefGoogle Scholar
  42. 42.
    Slater, D., Healey, G.: Physics-based model acquisition and identification in airborne spectral images. In: Int’l Conf. on Computer Vision, pp. 257–262, Vancouver, British Columbia, Canada, July 2001 Google Scholar
  43. 43.
    Sotoca, J.M., Pla, F., Klaren, A.C.: Unsupervised band selection for multispectral images using information theory. In: Int’l Conf. on Pattern Recognition, vol. 3, pp. 510–513, Cambridge, UK, August 2004 Google Scholar
  44. 44.
    Tenenbaum, J.B., Silva, V., Langford, J.C.: A global framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000) CrossRefGoogle Scholar
  45. 45.
    Tominaga, S.: A multi-channel vision system for estimating surface and illuminant functions. J. Opt. Soc. Am. A 13, 2163–2173 (1996) CrossRefGoogle Scholar
  46. 46.
    Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: IEEE Int’l Conf. on Computer Vision, pp. 281–288, Nice, France, October 2003 CrossRefGoogle Scholar
  47. 47.
    Wang, H., Angelopoulou, E.: Sensor band selection for multispectral imaging via average normalized information. J. Real-Time Image Process. 1(2), 109–121 (2006) CrossRefGoogle Scholar
  48. 48.
    Wasserman, L.: All of Statistics: A Concise Course in Statistical Inference. Springer Texts in Statistics (2005) Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • Andreas Koschan
    • 1
    Email author
  • Yi Yao
    • 2
  • Hong Chang
    • 1
  • Mongi Abidi
    • 1
  1. 1.Imaging, Robotics, and Intelligent Systems LabUniversity of TennesseeKnoxvilleUSA
  2. 2.Visualization and Computer Vision LabGE Global ResearchNiskayunaUSA

Personalised recommendations