Abstract

We present a face-recognition system based on the optical measurement of linear features. We describe a polarization-based optical system that computes linear projections of an incident irradiance distribution. We quantify the fundamental limitations of optical feature measurement. We find that higher feature fidelity can be obtained by feature-specific imaging than by postprocessing a conventional image. We present feature-fidelity results for wavelet, principal component, and Fisher features. We study face recognition by using a k-nearest neighbors classifier and two different feed-forward neural networks. Each image block is reduced to either a one- or a two-dimensional feature space for input to these recognition algorithms. As high as 99% recognition has been achieved with one-dimensional wavelet feature projections and 100% has been achieved with two-dimensional projections. A 95-fold increase in noise tolerance by use of feature-specific imaging has been demonstrated for an example of the face-recognition problem. An optical experiment is performed to validate these results.

© 2005 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. P. Christensen, G. W. Euliss, M. J. McFadden, K. M. Coyle, P. Milojkovic, M. W. Haney, J. van der Gracht, R. A. Athale, “Active-eyes: an adaptive pixel-by-pixel image-segmentation sensor architecture for high-dynamic-range hyperspectral imaging,” Appl. Opt. 41, 6093–6103 (2002).
    [CrossRef] [PubMed]
  2. W. C. Chou, M. A. Neifeld, R. Xuan, “Information-based optical design for binary valued imagery,” Appl. Opt. 39, 1731–1742 (2000).
    [CrossRef]
  3. C. J. Oliver, “Optical image processing by multiplex coding,” Appl. Opt. 15, 93–106 (1976).
    [CrossRef] [PubMed]
  4. A. Samal, P. Iyengar, “Automatic recognition and analysis of human faces and facial expressions: a survey,” Pattern Recogn. 25, 65–77 (1992).
    [CrossRef]
  5. R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
    [CrossRef]
  6. Z. Hong, “Algebraic feature extraction of image for recognition,” Pattern Recogn. 24, 211–219 (1991).
    [CrossRef]
  7. M. Kirby, L. Sirovich, “Application of the Karhunen–Loeve procedure for the characterization of human faces,” IEEE Trans. Pattern Anal. Mach. Intell. 12, 103–108 (1990).
    [CrossRef]
  8. A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
    [CrossRef]
  9. L. Sirovich, M. Kirby, “Low-dimensional procedure for the characterization of the human face,” J. Opt. Soc. Am. 4, 519–524 (1987).
    [CrossRef]
  10. M. A. Turk, A. P. Pentland, “Face recognition using eigenfaces,” in IEEE Society Conference on Computer Vision and Pattern Recognition (IEEE, New York, 1991), pp. 586–591.
  11. A. K. Jain, Fundamentals of Digital Image Processing (Prentice-Hall, Englewood Cliffs, N.J., 1989).
  12. P. A. Wintz, “Transform picture coding,” Proc. IEEE 60, 809–820 (1972).
    [CrossRef]
  13. M. Nixon, “Eye spacing measurement for facial recognition,” in Applications of Digital Image Processing VIII, A. G. Tescher, ed., Proc. SPIE575, 279–285 (1985).
    [CrossRef]
  14. S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).
  15. B. S. Manjunath, R. Chellappa, C. V. D. Malsburg, “A feature based approach to face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1992), pp. 373–378.
  16. A. Yuille, D. Cohen, P. Hallinan, “Feature extraction from faces using deformable templates,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1989), pp. 104–109.
    [CrossRef]
  17. M. J. Conlin, “A rule-based high level vision system,” Intelligent Robots and Computer Vision, D. P. Casasent, ed., Proc. SPIE726, 314–320 (1984).
    [CrossRef]
  18. D. Reisfeld, Y. Yeshuran, “Robust detection of facial features by generalized symmetry,” in Proceedings of 11th IAPR International Conference on Pattern Recognition (IEEE, New York, 1992), pp. 117–120.
    [CrossRef]
  19. P. B. Felgett, E. H. Linfoot, “On the assessment of the optical images,” Philos. Trans. R. Soc. London 247, 269–407 (1955).
    [CrossRef]
  20. M. A. Neifeld, P. Shankar, “Feature-specific imaging,” Appl. Opt. 42, 3379–3389 (2003).
    [CrossRef] [PubMed]
  21. M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
    [CrossRef] [PubMed]
  22. I. Daubechies, “The wavelet transform, time-frequency localization, and signal analysis,” IEEE Trans. Inf. Theory 36, 971–1005 (1990).
    [CrossRef]
  23. D. Solomon, Data Compression: The Complete Reference, 2nd ed. (Springer-Verlag, Berlin, 2000).
    [CrossRef]
  24. K. I. Diamantaras, S. Y. Kung, Principal Components Neural Networks: Theory and Applications (Wiley, New York, 1996), pp. 44–73.
  25. H. Feng, M. Effros, “On the rate-distortion performance and computational efficiency of the Karhunen–Loeve transform for lossy data compression,” IEEE Trans. Image Process. 11, 113–122 (2002).
    [CrossRef]
  26. S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.
  27. A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
    [CrossRef]
  28. R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2000).
  29. E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
    [CrossRef]
  30. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. (Prentice-Hall, Englewood Cliffs, N.J., 1999).

2003 (1)

2002 (2)

2000 (2)

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

W. C. Chou, M. A. Neifeld, R. Xuan, “Information-based optical design for binary valued imagery,” Appl. Opt. 39, 1731–1742 (2000).
[CrossRef]

1995 (1)

R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
[CrossRef]

1992 (2)

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

A. Samal, P. Iyengar, “Automatic recognition and analysis of human faces and facial expressions: a survey,” Pattern Recogn. 25, 65–77 (1992).
[CrossRef]

1991 (1)

Z. Hong, “Algebraic feature extraction of image for recognition,” Pattern Recogn. 24, 211–219 (1991).
[CrossRef]

1990 (2)

M. Kirby, L. Sirovich, “Application of the Karhunen–Loeve procedure for the characterization of human faces,” IEEE Trans. Pattern Anal. Mach. Intell. 12, 103–108 (1990).
[CrossRef]

I. Daubechies, “The wavelet transform, time-frequency localization, and signal analysis,” IEEE Trans. Inf. Theory 36, 971–1005 (1990).
[CrossRef]

1987 (1)

L. Sirovich, M. Kirby, “Low-dimensional procedure for the characterization of the human face,” J. Opt. Soc. Am. 4, 519–524 (1987).
[CrossRef]

1976 (1)

1972 (1)

P. A. Wintz, “Transform picture coding,” Proc. IEEE 60, 809–820 (1972).
[CrossRef]

1955 (1)

P. B. Felgett, E. H. Linfoot, “On the assessment of the optical images,” Philos. Trans. R. Soc. London 247, 269–407 (1955).
[CrossRef]

Akamatsu, S.

S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).

Antonini, M.

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

Athale, R. A.

Aysin, A.

A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
[CrossRef]

Barlaud, M.

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

Chaparro, L. F.

A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
[CrossRef]

Chellappa, R.

R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
[CrossRef]

B. S. Manjunath, R. Chellappa, C. V. D. Malsburg, “A feature based approach to face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1992), pp. 373–378.

Chou, W. C.

Christensen, M. P.

Cohen, D.

A. Yuille, D. Cohen, P. Hallinan, “Feature extraction from faces using deformable templates,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1989), pp. 104–109.
[CrossRef]

Conlin, M. J.

M. J. Conlin, “A rule-based high level vision system,” Intelligent Robots and Computer Vision, D. P. Casasent, ed., Proc. SPIE726, 314–320 (1984).
[CrossRef]

Coyle, K. M.

Daubechies, I.

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

I. Daubechies, “The wavelet transform, time-frequency localization, and signal analysis,” IEEE Trans. Inf. Theory 36, 971–1005 (1990).
[CrossRef]

Diamantaras, K. I.

K. I. Diamantaras, S. Y. Kung, Principal Components Neural Networks: Theory and Applications (Wiley, New York, 1996), pp. 44–73.

Duda, R. O.

R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2000).

Effros, M.

H. Feng, M. Effros, “On the rate-distortion performance and computational efficiency of the Karhunen–Loeve transform for lossy data compression,” IEEE Trans. Image Process. 11, 113–122 (2002).
[CrossRef]

Euliss, G. W.

Felgett, P. B.

P. B. Felgett, E. H. Linfoot, “On the assessment of the optical images,” Philos. Trans. R. Soc. London 247, 269–407 (1955).
[CrossRef]

Feng, H.

H. Feng, M. Effros, “On the rate-distortion performance and computational efficiency of the Karhunen–Loeve transform for lossy data compression,” IEEE Trans. Image Process. 11, 113–122 (2002).
[CrossRef]

Fukamachi, H.

S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).

Grave, I.

A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
[CrossRef]

Hallinan, P.

A. Yuille, D. Cohen, P. Hallinan, “Feature extraction from faces using deformable templates,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1989), pp. 104–109.
[CrossRef]

Haney, M. W.

Hart, P. E.

R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2000).

Haykin, S.

S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. (Prentice-Hall, Englewood Cliffs, N.J., 1999).

Hong, S. H.

S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.

Hong, Z.

Z. Hong, “Algebraic feature extraction of image for recognition,” Pattern Recogn. 24, 211–219 (1991).
[CrossRef]

Iyengar, P.

A. Samal, P. Iyengar, “Automatic recognition and analysis of human faces and facial expressions: a survey,” Pattern Recogn. 25, 65–77 (1992).
[CrossRef]

Jain, A. K.

A. K. Jain, Fundamentals of Digital Image Processing (Prentice-Hall, Englewood Cliffs, N.J., 1989).

Jung, S. B.

S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.

Kirby, M.

M. Kirby, L. Sirovich, “Application of the Karhunen–Loeve procedure for the characterization of human faces,” IEEE Trans. Pattern Anal. Mach. Intell. 12, 103–108 (1990).
[CrossRef]

L. Sirovich, M. Kirby, “Low-dimensional procedure for the characterization of the human face,” J. Opt. Soc. Am. 4, 519–524 (1987).
[CrossRef]

Kung, S. Y.

K. I. Diamantaras, S. Y. Kung, Principal Components Neural Networks: Theory and Applications (Wiley, New York, 1996), pp. 44–73.

Kwon, J. W.

S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.

Lee, S. J.

S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.

Linfoot, E. H.

P. B. Felgett, E. H. Linfoot, “On the assessment of the optical images,” Philos. Trans. R. Soc. London 247, 269–407 (1955).
[CrossRef]

Malsburg, C. V. D.

B. S. Manjunath, R. Chellappa, C. V. D. Malsburg, “A feature based approach to face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1992), pp. 373–378.

Manjunath, B. S.

B. S. Manjunath, R. Chellappa, C. V. D. Malsburg, “A feature based approach to face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1992), pp. 373–378.

Marszalec, E.

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

Martinkauppi, B.

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

Mathiew, M.

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

McFadden, M. J.

Milojkovic, P.

Moghaddam, B.

A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
[CrossRef]

Neifeld, M. A.

Nixon, M.

M. Nixon, “Eye spacing measurement for facial recognition,” in Applications of Digital Image Processing VIII, A. G. Tescher, ed., Proc. SPIE575, 279–285 (1985).
[CrossRef]

Oliver, C. J.

Pentland, A.

A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
[CrossRef]

Pentland, A. P.

M. A. Turk, A. P. Pentland, “Face recognition using eigenfaces,” in IEEE Society Conference on Computer Vision and Pattern Recognition (IEEE, New York, 1991), pp. 586–591.

Pietikäinen, M.

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

Reisfeld, D.

D. Reisfeld, Y. Yeshuran, “Robust detection of facial features by generalized symmetry,” in Proceedings of 11th IAPR International Conference on Pattern Recognition (IEEE, New York, 1992), pp. 117–120.
[CrossRef]

Samal, A.

A. Samal, P. Iyengar, “Automatic recognition and analysis of human faces and facial expressions: a survey,” Pattern Recogn. 25, 65–77 (1992).
[CrossRef]

Sasaki, T.

S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).

Shankar, P.

Shusterman, V.

A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
[CrossRef]

Sirohey, S.

R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
[CrossRef]

Sirovich, L.

M. Kirby, L. Sirovich, “Application of the Karhunen–Loeve procedure for the characterization of human faces,” IEEE Trans. Pattern Anal. Mach. Intell. 12, 103–108 (1990).
[CrossRef]

L. Sirovich, M. Kirby, “Low-dimensional procedure for the characterization of the human face,” J. Opt. Soc. Am. 4, 519–524 (1987).
[CrossRef]

Solomon, D.

D. Solomon, Data Compression: The Complete Reference, 2nd ed. (Springer-Verlag, Berlin, 2000).
[CrossRef]

Soriano, M.

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

Starner, T.

A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
[CrossRef]

Stork, D. G.

R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2000).

Suinaga, Y.

S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).

Turk, M.

A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
[CrossRef]

Turk, M. A.

M. A. Turk, A. P. Pentland, “Face recognition using eigenfaces,” in IEEE Society Conference on Computer Vision and Pattern Recognition (IEEE, New York, 1991), pp. 586–591.

van der Gracht, J.

Wilson, C.

R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
[CrossRef]

Wintz, P. A.

P. A. Wintz, “Transform picture coding,” Proc. IEEE 60, 809–820 (1972).
[CrossRef]

Xuan, R.

Yeshuran, Y.

D. Reisfeld, Y. Yeshuran, “Robust detection of facial features by generalized symmetry,” in Proceedings of 11th IAPR International Conference on Pattern Recognition (IEEE, New York, 1992), pp. 117–120.
[CrossRef]

Yuille, A.

A. Yuille, D. Cohen, P. Hallinan, “Feature extraction from faces using deformable templates,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1989), pp. 104–109.
[CrossRef]

Appl. Opt. (4)

IEEE Trans. Image Process. (2)

H. Feng, M. Effros, “On the rate-distortion performance and computational efficiency of the Karhunen–Loeve transform for lossy data compression,” IEEE Trans. Image Process. 11, 113–122 (2002).
[CrossRef]

M. Antonini, M. Barlaud, M. Mathiew, I. Daubechies, “Image coding using wavelet transform,” IEEE Trans. Image Process. 1, 205–220 (1992).
[CrossRef] [PubMed]

IEEE Trans. Inf. Theory (1)

I. Daubechies, “The wavelet transform, time-frequency localization, and signal analysis,” IEEE Trans. Inf. Theory 36, 971–1005 (1990).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

M. Kirby, L. Sirovich, “Application of the Karhunen–Loeve procedure for the characterization of human faces,” IEEE Trans. Pattern Anal. Mach. Intell. 12, 103–108 (1990).
[CrossRef]

J. Electron. Imaging (1)

E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietikäinen, “Physics-based face database for color research,” J. Electron. Imaging 9, 32–38 (2000).
[CrossRef]

J. Opt. Soc. Am. (1)

L. Sirovich, M. Kirby, “Low-dimensional procedure for the characterization of the human face,” J. Opt. Soc. Am. 4, 519–524 (1987).
[CrossRef]

Pattern Recogn. (2)

Z. Hong, “Algebraic feature extraction of image for recognition,” Pattern Recogn. 24, 211–219 (1991).
[CrossRef]

A. Samal, P. Iyengar, “Automatic recognition and analysis of human faces and facial expressions: a survey,” Pattern Recogn. 25, 65–77 (1992).
[CrossRef]

Philos. Trans. R. Soc. London (1)

P. B. Felgett, E. H. Linfoot, “On the assessment of the optical images,” Philos. Trans. R. Soc. London 247, 269–407 (1955).
[CrossRef]

Proc. IEEE (2)

R. Chellappa, C. Wilson, S. Sirohey, “Human and machine recognition of faces: a survey,” Proc. IEEE 83, 705–740 (1995).
[CrossRef]

P. A. Wintz, “Transform picture coding,” Proc. IEEE 60, 809–820 (1972).
[CrossRef]

Other (15)

M. Nixon, “Eye spacing measurement for facial recognition,” in Applications of Digital Image Processing VIII, A. G. Tescher, ed., Proc. SPIE575, 279–285 (1985).
[CrossRef]

S. Akamatsu, T. Sasaki, H. Fukamachi, Y. Suinaga, “A robust face identification scheme—KL expansion of an invariant feature space,” in Intelligent Robots and Computer Vision X: Algorithms and Techniques, D. P. Casasent, ed., Proc. SPIE1607, 71–84 (1991).

B. S. Manjunath, R. Chellappa, C. V. D. Malsburg, “A feature based approach to face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1992), pp. 373–378.

A. Yuille, D. Cohen, P. Hallinan, “Feature extraction from faces using deformable templates,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1989), pp. 104–109.
[CrossRef]

M. J. Conlin, “A rule-based high level vision system,” Intelligent Robots and Computer Vision, D. P. Casasent, ed., Proc. SPIE726, 314–320 (1984).
[CrossRef]

D. Reisfeld, Y. Yeshuran, “Robust detection of facial features by generalized symmetry,” in Proceedings of 11th IAPR International Conference on Pattern Recognition (IEEE, New York, 1992), pp. 117–120.
[CrossRef]

A. Pentland, B. Moghaddam, T. Starner, M. Turk, “View-based and modular eigenspaces for face recognition,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994), pp. 84–91.
[CrossRef]

M. A. Turk, A. P. Pentland, “Face recognition using eigenfaces,” in IEEE Society Conference on Computer Vision and Pattern Recognition (IEEE, New York, 1991), pp. 586–591.

A. K. Jain, Fundamentals of Digital Image Processing (Prentice-Hall, Englewood Cliffs, N.J., 1989).

D. Solomon, Data Compression: The Complete Reference, 2nd ed. (Springer-Verlag, Berlin, 2000).
[CrossRef]

K. I. Diamantaras, S. Y. Kung, Principal Components Neural Networks: Theory and Applications (Wiley, New York, 1996), pp. 44–73.

S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. (Prentice-Hall, Englewood Cliffs, N.J., 1999).

S. J. Lee, S. B. Jung, J. W. Kwon, S. H. Hong, “Face detection and recognition using PCA,” in TENCON 99, Proceedings of IEEE Regional Conference (Institute of Electrical and Electronics Engineers, New York, 1999), Vol. 1, pp. 84–87.

A. Aysin, L. F. Chaparro, I. Grave, V. Shusterman, “Denoising of nonstationary signals using optimized Karhunen–Loeve expansion,” in Proceedings of IEEE International Symposium Time-Frequency and Time-Scale Analysis (Institute of Electrical and Electronics Engineers, New York, 1998), pp. 621–624.
[CrossRef]

R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed. (Wiley, New York, 2000).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (8)

Fig. 1
Fig. 1

Schematic depicting two approaches to feature extraction: (a) conventional imaging with postprocessing; (b) task-specific imaging that uses optical processing for feature extraction before electronic detection.

Fig. 2
Fig. 2

Candidate feature-specific imaging architecture: detectors for the positive and negative components, D1 +, D1 −, of the first feature measurement and, D2 +, D2 −, for the second feature.

Fig. 3
Fig. 3

Plot of feature RMSE versus the number of measured features for several block sizes with σ = 20: (a) wavelet features, (b) PCA features, (c) FLD features. Solid curves, RMSE achieved by using feature-specific imaging; dashed lines, performance of the postprocessing of a conventional image. Note that for small numbers of features the feature-specific approach offers a lower RMSE than the conventional approach.

Fig. 4
Fig. 4

Example face images from the training database. (a) Example images from 7 of the 10 different classes, (b) images representing the within-class variation.

Fig. 5
Fig. 5

Plot of recognition performance versus feature index for the three algorithms: 9-NN, BP1 with 6 hidden units, and BP2 with 20 hidden units. These data are based on 16 × 16 pixel blocks: (a) wavelet features, (b) PCA features, (c) FLD features.

Fig. 6
Fig. 6

Recognition performance with two-dimensional projections (i.e., two features per block) for the three algorithms: 9-NN, BP1 with 6 hidden units, and BP2 with 20 hidden units. These data are based on 16 × 16 pixel blocks and (a) wavelet feature pairs, (b) PCA feature pairs, and (c) FLD feature pairs.

Fig. 7
Fig. 7

Recognition performance versus measurement noise for one-dimensional projections. Data are based on the best noise-free feature from wavelet, PCA, and FLD classes. Features obtained with, solid curve, feature-specific and, dashed line, conventional imagers are compared with three difference recognition algorithms: (a) BP1 with 6 hidden units, (b) BP2 with 20 hidden units, (c) k-NN (k = 9).

Fig. 8
Fig. 8

Recognition performance versus measurement noise for one-dimensional projections. Data are based on the PCA feature corresponding to the largest eigenvalue. Features experimentally obtained with, solid curves, feature-specific (fs) and, dashed curves, conventional (conv) imagers are compared by using three different recognition algorithms, kNN (k = 9), BP1 with 6 hidden units, BP2 with 20 hidden units.

Tables (4)

Tables Icon

Table 1 Number of Features Producing Greater than 95% Successful Recognition for Various Block Sizes and Recognition Algorithms

Tables Icon

Table 2 Number of Feature Pairs Producing Greater than 98% Successful Recognition for Various Block Sizes and Recognition Algorithms

Tables Icon

Table 3 Threshold AWGN Strength (σmax) beyond which 96% Successful Recognition Performance cannot be Achieved with One-Dimensional Projections

Tables Icon

Table 4 Threshold AWGN Strength (σmax) beyond which 96% Successful Recognition Performance cannot be Achieved with Two-Dimensional Projections

Equations (2)

Equations on this page are rendered with MathJax. Learn more.

S B = i = 1 c n i ( m i m ) ( m i m ) t ,
S w = i = 1 c x D i ( x m i ) ( x m i ) t

Metrics