Abstract

A method for distortion-tolerant recognition of objects in water using three-dimensional (3D) integral imaging with a neural network classification architecture is presented. Recognition algorithms are developed and experimental results are presented with rotation-variable 3D objects. To test the robustness of the system, objects are placed under a variety of water conditions, including variable Maalox-induced scattering levels and occlusion using pine needles. Neural networks have long been used for two-dimensional recognition and have recently been used for 3D digital holographic recognition. To the best of our knowledge, this is the first use of neural networks for passive 3D integral imaging and recognition of underwater objects.

© 2010 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. G. Lippmann, “Epreuves reversibles donnant la sensation du relief,” J. Phys. (Paris) 7, 821-825 (1908).
  2. H. E. Ives, “Optical properties of a Lippmann lenticulated sheet,” J. Opt. Soc. Am. 21, 171-176 (1931).
    [CrossRef]
  3. C. B. Burckhardt, “Optimum parameters and resolution limitation of integral photography,” J. Opt. Soc. Am. 58, 71-76 (1968).
    [CrossRef]
  4. Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
    [CrossRef]
  5. T. Okoshi, “Three-dimensional displays,” Proc. IEEE 68, 548-564 (1980).
    [CrossRef]
  6. S.Benton, ed., Selected Papers on Three-Dimensional Displays (SPIE, 2001).
  7. J.-S. Jang and B. Javidi, “Improved viewing resolution of three-dimensional integral imaging by use of nonstationary micro-optics,” Opt. Lett. 27, 324-326 (2002).
    [CrossRef]
  8. M. C. Forman, N. Davies, and M. McCormick, “Continuous parallax in discrete pixelated integral three-dimensional displays,” J. Opt. Soc. Am. A 20, 411-421 (2003).
    [CrossRef]
  9. R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
    [CrossRef]
  10. J. Arai, H. Hoshino, M. Okui, and F. Okano, “Effects of focusing on the resolution characteristics of integral photography,” J. Opt. Soc. Am. A 20, 996-1004 (2003).
    [CrossRef]
  11. J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
    [CrossRef]
  12. J. Arai, M. Okui, M. Kobayashi, and F. Okano, “Geometrical effects of positional errors in integral photography,” J. Opt. Soc. Am. A 21, 951-958 (2004).
    [CrossRef]
  13. A. Stern and B. Javidi, “Three-dimensional image sensing, visualization, and processing using integral imaging,” Proc. IEEE 94, 591-607 (2006).
    [CrossRef]
  14. Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
    [CrossRef]
  15. B.Javidi, F.Okano, and J.Son, eds., Three Dimensional Imaging, Visualization, and Display Technology (Springer, 2008).
  16. R. Schulein and B. Javidi, “Underwater multi-view three-dimensional imaging,” J. Disp. Technol. 4, 351-353 (2008).
    [CrossRef]
  17. F.Sadjadi, ed., Selected Papers on Automatic Target Recognition (SPIE-CDROM, 2000).
  18. F. Sadjadi and A. Mahalonobis, “Target adaptive polarimetric SAR target discrimination using MACH filters,” Appl. Opt. 45, 7365-7374 (2006).
    [CrossRef]
  19. F. Dubois, “Automatic spatial frequency selection algorithm for pattern recognition by correlation,” Appl. Opt. 32, 4365-4371 (1993).
    [CrossRef] [PubMed]
  20. O. Matoba, E. Tajahuerce, and B. Javidi, “Real-time three-dimensional object recognition with multiple perspectives imaging,” Appl. Opt. 40, 3318-3325 (2001).
    [CrossRef]
  21. B. Javidi, R. Ponce-Díaz, and S.-H. Hong, “Three-dimensional recognition of occluded objects by using computational integral imaging,” Opt. Lett. 31, 1106-1108 (2006).
    [CrossRef] [PubMed]
  22. S. Yeom and B. Javidi, “Three-dimensional distortion-tolerant object recognition using integral imaging,” Opt. Express 12, 5795-5809 (2004).
    [CrossRef] [PubMed]
  23. C. Do, R. Martínez-Cuenca, and B. Javidi, “Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis,” J. Opt. Soc. Am. A 26, 245-251 (2009).
    [CrossRef]
  24. H. Murakami and B. Kumar, “Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 511-515 (1982).
    [CrossRef]
  25. R. Schalkhoff, Pattern Recognition, Statistical, Structural and Neural Approaches (Wiley, 1992).
  26. S. Haykin, Neural Networks: A Comprehensive Foundation (Macmillan, 1994).
  27. C. M. Bishop, Neural Networks for Pattern Recognition (Oxford U. Press, 1995).
  28. Y. Frauel and B. Javidi, “Neural network for three-dimensional object recognition based on digital holography,” Opt. Lett. 26, 1478-1480 (2001).
    [CrossRef]
  29. H. Kwon and N. M. Nasrabadi, “Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens. 43, 388-397 (2005).
    [CrossRef]
  30. A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
    [CrossRef]
  31. P. Refregier, Noise Theory and Application to Physics (Springer, 2003).
  32. A. K. Jain, Fundamentals of Digital Image Processing (Prentice-Hall, 1989).
  33. R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Pearson Prentice Hall, 2004).

2009 (2)

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

C. Do, R. Martínez-Cuenca, and B. Javidi, “Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis,” J. Opt. Soc. Am. A 26, 245-251 (2009).
[CrossRef]

2008 (1)

R. Schulein and B. Javidi, “Underwater multi-view three-dimensional imaging,” J. Disp. Technol. 4, 351-353 (2008).
[CrossRef]

2006 (4)

A. Stern and B. Javidi, “Three-dimensional image sensing, visualization, and processing using integral imaging,” Proc. IEEE 94, 591-607 (2006).
[CrossRef]

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

B. Javidi, R. Ponce-Díaz, and S.-H. Hong, “Three-dimensional recognition of occluded objects by using computational integral imaging,” Opt. Lett. 31, 1106-1108 (2006).
[CrossRef] [PubMed]

F. Sadjadi and A. Mahalonobis, “Target adaptive polarimetric SAR target discrimination using MACH filters,” Appl. Opt. 45, 7365-7374 (2006).
[CrossRef]

2005 (1)

H. Kwon and N. M. Nasrabadi, “Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens. 43, 388-397 (2005).
[CrossRef]

2004 (2)

2003 (3)

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

M. C. Forman, N. Davies, and M. McCormick, “Continuous parallax in discrete pixelated integral three-dimensional displays,” J. Opt. Soc. Am. A 20, 411-421 (2003).
[CrossRef]

J. Arai, H. Hoshino, M. Okui, and F. Okano, “Effects of focusing on the resolution characteristics of integral photography,” J. Opt. Soc. Am. A 20, 996-1004 (2003).
[CrossRef]

2002 (2)

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

J.-S. Jang and B. Javidi, “Improved viewing resolution of three-dimensional integral imaging by use of nonstationary micro-optics,” Opt. Lett. 27, 324-326 (2002).
[CrossRef]

2001 (2)

1993 (1)

1982 (1)

H. Murakami and B. Kumar, “Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 511-515 (1982).
[CrossRef]

1980 (1)

T. Okoshi, “Three-dimensional displays,” Proc. IEEE 68, 548-564 (1980).
[CrossRef]

1978 (1)

Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
[CrossRef]

1968 (1)

1931 (1)

1908 (1)

G. Lippmann, “Epreuves reversibles donnant la sensation du relief,” J. Phys. (Paris) 7, 821-825 (1908).

Arai, J.

Bahn, J. -E.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Billmers, R.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Bishop, C. M.

C. M. Bishop, Neural Networks for Pattern Recognition (Oxford U. Press, 1995).

Burckhardt, C. B.

Choi, H.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Choi, Y. -J.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Concannon, B.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Contarino, V.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Davies, N.

Davis, J.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Do, C.

Dubois, F.

Eddins, S. L.

R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Pearson Prentice Hall, 2004).

Forman, M. C.

Frauel, Y.

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

Y. Frauel and B. Javidi, “Neural network for three-dimensional object recognition based on digital holography,” Opt. Lett. 26, 1478-1480 (2001).
[CrossRef]

Gonzalez, R. C.

R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Pearson Prentice Hall, 2004).

Haykin, S.

S. Haykin, Neural Networks: A Comprehensive Foundation (Macmillan, 1994).

Hong, S. -H.

Hoshino, H.

Igarashi, Y.

Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
[CrossRef]

Ives, H. E.

Jain, A. K.

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

Jang, J. -S.

Javidi, B.

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

C. Do, R. Martínez-Cuenca, and B. Javidi, “Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis,” J. Opt. Soc. Am. A 26, 245-251 (2009).
[CrossRef]

R. Schulein and B. Javidi, “Underwater multi-view three-dimensional imaging,” J. Disp. Technol. 4, 351-353 (2008).
[CrossRef]

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

A. Stern and B. Javidi, “Three-dimensional image sensing, visualization, and processing using integral imaging,” Proc. IEEE 94, 591-607 (2006).
[CrossRef]

B. Javidi, R. Ponce-Díaz, and S.-H. Hong, “Three-dimensional recognition of occluded objects by using computational integral imaging,” Opt. Lett. 31, 1106-1108 (2006).
[CrossRef] [PubMed]

S. Yeom and B. Javidi, “Three-dimensional distortion-tolerant object recognition using integral imaging,” Opt. Express 12, 5795-5809 (2004).
[CrossRef] [PubMed]

J.-S. Jang and B. Javidi, “Improved viewing resolution of three-dimensional integral imaging by use of nonstationary micro-optics,” Opt. Lett. 27, 324-326 (2002).
[CrossRef]

Y. Frauel and B. Javidi, “Neural network for three-dimensional object recognition based on digital holography,” Opt. Lett. 26, 1478-1480 (2001).
[CrossRef]

O. Matoba, E. Tajahuerce, and B. Javidi, “Real-time three-dimensional object recognition with multiple perspectives imaging,” Appl. Opt. 40, 3318-3325 (2001).
[CrossRef]

Kim, S. -K.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Kobayashi, M.

Kumar, B.

H. Murakami and B. Kumar, “Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 511-515 (1982).
[CrossRef]

Kwon, H.

H. Kwon and N. M. Nasrabadi, “Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens. 43, 388-397 (2005).
[CrossRef]

Laux, A.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Lippmann, G.

G. Lippmann, “Epreuves reversibles donnant la sensation du relief,” J. Phys. (Paris) 7, 821-825 (1908).

Mahalonobis, A.

Martinez-Corral, M.

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

Martinez-Cuenca, R.

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

Martínez-Cuenca, R.

Matoba, O.

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

O. Matoba, E. Tajahuerce, and B. Javidi, “Real-time three-dimensional object recognition with multiple perspectives imaging,” Appl. Opt. 40, 3318-3325 (2001).
[CrossRef]

McCormick, M.

Mullen, L.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Murakami, H.

H. Murakami and B. Kumar, “Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 511-515 (1982).
[CrossRef]

Murata, H.

Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
[CrossRef]

Nasrabadi, N. M.

H. Kwon and N. M. Nasrabadi, “Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens. 43, 388-397 (2005).
[CrossRef]

Naughton, T.

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

Okano, F.

Okoshi, T.

T. Okoshi, “Three-dimensional displays,” Proc. IEEE 68, 548-564 (1980).
[CrossRef]

Okui, M.

Ponce-Díaz, R.

Prentice, J.

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

Refregier, P.

P. Refregier, Noise Theory and Application to Physics (Springer, 2003).

Saavedra, G.

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

Sadjadi, F.

Saveljev, V. V.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Schalkhoff, R.

R. Schalkhoff, Pattern Recognition, Statistical, Structural and Neural Approaches (Wiley, 1992).

Schulein, R.

R. Schulein and B. Javidi, “Underwater multi-view three-dimensional imaging,” J. Disp. Technol. 4, 351-353 (2008).
[CrossRef]

Son, J. -Y.

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Stern, A.

A. Stern and B. Javidi, “Three-dimensional image sensing, visualization, and processing using integral imaging,” Proc. IEEE 94, 591-607 (2006).
[CrossRef]

Tahajuerce, E.

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

Tajahuerce, E.

Ueda, M.

Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
[CrossRef]

Woods, R. E.

R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Pearson Prentice Hall, 2004).

Yeom, S.

Appl. Opt. (3)

IEEE Trans. Geosci. Remote Sens. (1)

H. Kwon and N. M. Nasrabadi, “Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery,” IEEE Trans. Geosci. Remote Sens. 43, 388-397 (2005).
[CrossRef]

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

H. Murakami and B. Kumar, “Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Anal. Mach. Intell. PAMI-4, 511-515 (1982).
[CrossRef]

J. Disp. Technol. (1)

R. Schulein and B. Javidi, “Underwater multi-view three-dimensional imaging,” J. Disp. Technol. 4, 351-353 (2008).
[CrossRef]

J. Mod. Opt. (1)

A. Laux, R. Billmers, L. Mullen, B. Concannon, J. Davis, J. Prentice, and V. Contarino, “The a, b, c s of oceanographic lidar predictions: a significant step towards closing the loop between theory and experiment,” J. Mod. Opt. 49, 439-451 (2002).
[CrossRef]

J. Opt. Soc. Am. (2)

J. Opt. Soc. Am. A (4)

J. Phys. (Paris) (1)

G. Lippmann, “Epreuves reversibles donnant la sensation du relief,” J. Phys. (Paris) 7, 821-825 (1908).

Jpn. J. Appl. Phys. (1)

Y. Igarashi, H. Murata, and M. Ueda, “3D display system using a computer-generated integral photograph,” Jpn. J. Appl. Phys. 17, 1683-1684 (1978).
[CrossRef]

Opt. Eng. (Bellingham) (1)

J.-Y. Son, V. V. Saveljev, Y.-J. Choi, J.-E. Bahn, S.-K. Kim, and H. Choi, “Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,” Opt. Eng. (Bellingham) 42, 3326-3333 (2003).
[CrossRef]

Opt. Express (1)

Opt. Lett. (3)

Proc. IEEE (4)

T. Okoshi, “Three-dimensional displays,” Proc. IEEE 68, 548-564 (1980).
[CrossRef]

R. Martinez-Cuenca, G. Saavedra, M. Martinez-Corral, and B. Javidi, “Progress in 3-D multiperspective display by integral imaging,” Proc. IEEE 97, 1067-1077 (2009).
[CrossRef]

A. Stern and B. Javidi, “Three-dimensional image sensing, visualization, and processing using integral imaging,” Proc. IEEE 94, 591-607 (2006).
[CrossRef]

Y. Frauel, T. Naughton, O. Matoba, E. Tahajuerce, and B. Javidi, “Three dimensional imaging and display using computational holographic imaging,” Proc. IEEE 94, 636-653 (2006).
[CrossRef]

Other (9)

B.Javidi, F.Okano, and J.Son, eds., Three Dimensional Imaging, Visualization, and Display Technology (Springer, 2008).

S.Benton, ed., Selected Papers on Three-Dimensional Displays (SPIE, 2001).

F.Sadjadi, ed., Selected Papers on Automatic Target Recognition (SPIE-CDROM, 2000).

P. Refregier, Noise Theory and Application to Physics (Springer, 2003).

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

R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using Matlab (Pearson Prentice Hall, 2004).

R. Schalkhoff, Pattern Recognition, Statistical, Structural and Neural Approaches (Wiley, 1992).

S. Haykin, Neural Networks: A Comprehensive Foundation (Macmillan, 1994).

C. M. Bishop, Neural Networks for Pattern Recognition (Oxford U. Press, 1995).

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 (9)

Fig. 1
Fig. 1

System diagram of the proposed underwater 3D integral imaging neural networks recognition architecture. For training, 3D integral images are taken of N object classes at various rotation angles in air. For testing, 3D integral images are taken of the same classes at various rotation angles in variable scattering levels of water with and without occlusion. Multiple 3D computational reconstruction planes of training and testing integral images are computed and are preprocessed before going through PCA data reduction. Test images are compared to training images through neural networks and a class decision is made.

Fig. 2
Fig. 2

Optical pickup process for 3D integral imaging using microlens arrays for (a) in-air imaging environments and (b) underwater imaging environments. O i are elemental images from different perspectives.

Fig. 3
Fig. 3

Multilayer neural network schematic diagram.

Fig. 4
Fig. 4

Object Classes (a) 1, (b) 2, (c) 3, (d) 4, (e) 5, and (f) 6 used in the recognition experiment.

Fig. 5
Fig. 5

Experimental setup for testing objects in the heaviest concentration of Maalox, c 12 m 1 , in water with foreground and background pine needle occlusions. The fish object appears very blurred due to scattering caused by the addition of Maalox to water.

Fig. 6
Fig. 6

Central 2D elemental image of object Class 1 taken (a) in air for training purposes and (b) the heaviest concentration of Maalox, c 12 m 1 , in water with foreground and background pine needle occlusions. With traditional 2D imaging methods, it is very difficult to see the object in the heavy Maalox water with occlusion setting.

Fig. 7
Fig. 7

Central 2D elemental images of all class objects at 0° rotation angle under training and all testing conditions. c X m 1 indicates the attenuation coefficient of Maalox levels in water. Higher values of “c” present higher Maalox concentrations and greater in-water absorption and scattering levels. The Maalox concentration increases from top to bottom images. Each concentration of Maalox test is performed with and without pine needle occlusions.

Fig. 8
Fig. 8

Central 2D elemental images of Classes 1 and 4 for in-air training and the heaviest concentration of Maalox, c 12 m 1 , in water with pine needle occlusion testing at different rotation angles. Objects are very difficult to identify under heavy scattering and occlusion with traditional 2D imaging.

Fig. 9
Fig. 9

Range of 3D reconstructions for object Classes 1 and 4 rotated at + 45 ° for in-air training and the heaviest concentration of Maalox, c 12 m 1 , in water with occlusion testing. Images at the top show closer reconstruction planes and images at the bottom show further reconstruction planes. Objects behind occlusion are much easier to identify in 3D reconstructions than in the 2D images shown in Fig. 8.

Tables (1)

Tables Icon

Table 1 Experimental Classification Performance Results for Heavy Scattering Test Cases a

Equations (14)

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

O k l ( x , y ) = I ( k M p x μ x + u , l M p y μ y + v ) ,
u = 0 , 1 , , ( k + 1 ) M p x μ x ,     v = 0 , 1 , , ( l + 1 ) M p y μ y ,
I R ( x , y ; z R ) = 1 K L k = 0 K 1 l = 0 L 1 O k l ( u s x , v s y ) ,
s x = k M p x f μ x z R ,     s y = l M p y f μ y z R ,
s x = k M p x f μ x ( z air + z water n water ) ,     s y = l M p y f μ y ( z air + z water n water ) .
I R ( x , y ; z R ) = [ I R ( x , y , z R ) x I R ( x , y , z R ) y ] ,
| I R ( x , y ; z R ) | = ( I R ( x , y ; z R ) x ) 2 + ( I R ( x , y ; z R ) y ) 2 .
I out ( x , y ; z R ) = α | I R ( x , y ; z R ) | β α | I R ( x , y ; z R ) | β ,
x class = 1 N a = a min a max z R = z min z max [ x ; column ( I out a , class ( x , y ; z R ) ) ] ,
u 1 T S u 1 = λ 1 ,
S = U λ U T ,
x PCA = W PCA T x ,
y k ( x , w ) = σ ( a k ) = σ ( j = 0 H w k j ( 2 ) z j ) = σ ( j = 0 H w k j ( 2 ) h ( a j ) ) = σ ( j = 0 H w k j ( 2 ) h ( i = 0 M w j i ( 1 ) x i ) ) ,
h ( x ) = e x e x e x + e x ,     σ ( x ) = 1 1 + e x .

Metrics