Abstract

In many image processing applications, it is desirable to combine partially overlapping images into one larger scene. We introduce a supervised correlation filter method that automatically detects overlapping image pairs and estimates proper alignment. We use on-line composite filter design to achieve rotation- and overlap-invariant image pairing. We present stochastic system analysis that provides closed-form expressions that predict correlation plane response distribution, defines an overlap-invariant filter bank architecture, and obtains the optimum training set size. The resulting high-level image processing method is numerically efficient, suited for optoelectronic implementation, and competitive with manual reconstruction in speed and accuracy.

© 1999 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
    [CrossRef]
  2. L. G. Brown, “A survey of image registration techniques,” ACM (Assoc. Comput. Mach.) Comput. Surv. 24, 325–376 (1992).
    [CrossRef]
  3. Liang-Chien Chen, Liang-Hwei Lee, “Progressive generation of control frameworks for image registration,” Am. Soc. Photogrammetry Remote Sens. 58, 1321–1328 (1992).
  4. H. Freeman, “Computer processing of line drawn images,” ACM (Assoc. Comput. Mach.) Comput. Surv. 6, 57–97 (1974).
    [CrossRef]
  5. S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
    [CrossRef]
  6. G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
    [CrossRef]
  7. K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).
  8. W. E. L. Grimson, T. Lozano-Perez, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 469–482 (1987).
    [CrossRef]
  9. E. De Castro, C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 700–703 (1987).
    [CrossRef]
  10. C. F. Hester, D. Casasent, “Multivariant technique for multiclass pattern recognition,” Appl. Opt. 19, 1758–1761 (1980).
    [CrossRef] [PubMed]
  11. B. V. K. Vijaya Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
    [CrossRef]
  12. B. V. K. Vijaya Kumar, E. Pochapsky, “Signal-to-noise ratio considerations in modified matched spatial filters,” J. Opt. Soc. Am. A 3, 777–786 (1986).
    [CrossRef]
  13. D. Casasent, S. A. Liebowitz, A. Mahalanobis, “Parameter selection for iconic and symbolic pattern recognition filters,” in Optical and Digital Pattern Recognition, H. Liu, P. S. Schenker, eds., Proc. SPIE754, 284–303 (1987).
    [CrossRef]
  14. G. F. Schils, D. W. Sweeney, “Optical processor for recognition of 3-D targets viewed from any direction,” J. Opt. Soc. Am. A 5, 1309–1321 (1988).
    [CrossRef]
  15. L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
    [CrossRef]
  16. M. Rahmati, L. G. Hassebrook, “Intensity- and distortion-invariant pattern recognition with complex linear morphology,” Pattern Recogn. 27, 549–568 (1994).
    [CrossRef]
  17. M. E. Lhamon, L. G. Hassebrook, “Translation-invariant optical pattern recognition without correlation,” Opt. Eng. 35, 2700–2709 (1996).
    [CrossRef]
  18. L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
    [CrossRef]
  19. W. J. Chimitt, L. G. Hassebrook, “Automatic scene reconstruction from partially overlapping images using on line filter design,” in Optical Pattern Recognition IX, D. P. Casasent, T. H. Chao, eds., Proc. SPIE3386, 171–181 (1998).
    [CrossRef]
  20. H. L. Van Trees, Detection, Estimation and Modulation Theory (Wiley, New York, 1968), pp. 30 and 258.
  21. M. E. Lhamon, “Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems,” Ph.D. dissertation (University of Kentucky, Lexington, Ky., 1997).
  22. Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
    [CrossRef] [PubMed]
  23. Yuan-Neng Hsu, H. H. Arsenault, “Pattern discrimination by multiple circular harmonic components,” Appl. Opt. 23, 841–844 (1984).
    [CrossRef] [PubMed]
  24. R. W. Cohn, L. G. Hassebrook, “Representations of fully complex functions on real-time spatial light modulators,” in Optical Pattern Recognition, F. S. Yu, S. Jutamulia, eds. (Cambridge U. Press, New York, 1998), Chap. 15, p. 404.
  25. R. R. Kallman, P. Roth, T. Turpin, “Correlation results using invariant filters in an acousto-optic correlator,” in Optical Pattern Recognition V, D. P. Casasent, T.-H. Chao, eds., Proc. SPIE2237, 62–73 (1994).
    [CrossRef]
  26. R. J. Sharer, The Ancient Maya, 5th ed. (Stanford U. Press, Stanford, Calif., 1994), p. 324.
  27. S. Wels, Titanic, Legacy of the New World's Greatest Ocean Liner (Tehabi, Del Mar, Calif., 1997), image on cover.

1997 (1)

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

1996 (2)

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

M. E. Lhamon, L. G. Hassebrook, “Translation-invariant optical pattern recognition without correlation,” Opt. Eng. 35, 2700–2709 (1996).
[CrossRef]

1994 (1)

M. Rahmati, L. G. Hassebrook, “Intensity- and distortion-invariant pattern recognition with complex linear morphology,” Pattern Recogn. 27, 549–568 (1994).
[CrossRef]

1993 (1)

S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
[CrossRef]

1992 (4)

L. G. Brown, “A survey of image registration techniques,” ACM (Assoc. Comput. Mach.) Comput. Surv. 24, 325–376 (1992).
[CrossRef]

Liang-Chien Chen, Liang-Hwei Lee, “Progressive generation of control frameworks for image registration,” Am. Soc. Photogrammetry Remote Sens. 58, 1321–1328 (1992).

L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
[CrossRef]

B. V. K. Vijaya Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
[CrossRef]

1991 (1)

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

1990 (1)

L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
[CrossRef]

1988 (1)

1987 (2)

W. E. L. Grimson, T. Lozano-Perez, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 469–482 (1987).
[CrossRef]

E. De Castro, C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 700–703 (1987).
[CrossRef]

1986 (1)

1984 (1)

1982 (1)

G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
[CrossRef]

1980 (1)

1974 (1)

H. Freeman, “Computer processing of line drawn images,” ACM (Assoc. Comput. Mach.) Comput. Surv. 6, 57–97 (1974).
[CrossRef]

Arsenault, H. H.

Asano, T.

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

Benett, S.

G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
[CrossRef]

Brown, L. G.

L. G. Brown, “A survey of image registration techniques,” ACM (Assoc. Comput. Mach.) Comput. Surv. 24, 325–376 (1992).
[CrossRef]

Casasent, D.

C. F. Hester, D. Casasent, “Multivariant technique for multiclass pattern recognition,” Appl. Opt. 19, 1758–1761 (1980).
[CrossRef] [PubMed]

D. Casasent, S. A. Liebowitz, A. Mahalanobis, “Parameter selection for iconic and symbolic pattern recognition filters,” in Optical and Digital Pattern Recognition, H. Liu, P. S. Schenker, eds., Proc. SPIE754, 284–303 (1987).
[CrossRef]

Chatterjee, J.

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

Chen, Liang-Chien

Liang-Chien Chen, Liang-Hwei Lee, “Progressive generation of control frameworks for image registration,” Am. Soc. Photogrammetry Remote Sens. 58, 1321–1328 (1992).

Chimitt, W. J.

W. J. Chimitt, L. G. Hassebrook, “Automatic scene reconstruction from partially overlapping images using on line filter design,” in Optical Pattern Recognition IX, D. P. Casasent, T. H. Chao, eds., Proc. SPIE3386, 171–181 (1998).
[CrossRef]

Cohn, R. W.

R. W. Cohn, L. G. Hassebrook, “Representations of fully complex functions on real-time spatial light modulators,” in Optical Pattern Recognition, F. S. Yu, S. Jutamulia, eds. (Cambridge U. Press, New York, 1998), Chap. 15, p. 404.

De Castro, E.

E. De Castro, C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 700–703 (1987).
[CrossRef]

Evans, J.

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

Freeman, H.

H. Freeman, “Computer processing of line drawn images,” ACM (Assoc. Comput. Mach.) Comput. Surv. 6, 57–97 (1974).
[CrossRef]

Fukunaga, K.

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

Grimson, W. E. L.

W. E. L. Grimson, T. Lozano-Perez, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 469–482 (1987).
[CrossRef]

Hassebrook, L. G.

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

M. E. Lhamon, L. G. Hassebrook, “Translation-invariant optical pattern recognition without correlation,” Opt. Eng. 35, 2700–2709 (1996).
[CrossRef]

M. Rahmati, L. G. Hassebrook, “Intensity- and distortion-invariant pattern recognition with complex linear morphology,” Pattern Recogn. 27, 549–568 (1994).
[CrossRef]

L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
[CrossRef]

L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
[CrossRef]

W. J. Chimitt, L. G. Hassebrook, “Automatic scene reconstruction from partially overlapping images using on line filter design,” in Optical Pattern Recognition IX, D. P. Casasent, T. H. Chao, eds., Proc. SPIE3386, 171–181 (1998).
[CrossRef]

R. W. Cohn, L. G. Hassebrook, “Representations of fully complex functions on real-time spatial light modulators,” in Optical Pattern Recognition, F. S. Yu, S. Jutamulia, eds. (Cambridge U. Press, New York, 1998), Chap. 15, p. 404.

Hester, C. F.

Hostetler, L.

L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
[CrossRef]

Hsu, Yuan-Neng

Izumi, M.

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

Kallman, R. R.

R. R. Kallman, P. Roth, T. Turpin, “Correlation results using invariant filters in an acousto-optic correlator,” in Optical Pattern Recognition V, D. P. Casasent, T.-H. Chao, eds., Proc. SPIE2237, 62–73 (1994).
[CrossRef]

Kittler, J.

S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
[CrossRef]

Knapp, C.

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

Kopstein, S.

G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
[CrossRef]

Lee, Liang-Hwei

Liang-Chien Chen, Liang-Hwei Lee, “Progressive generation of control frameworks for image registration,” Am. Soc. Photogrammetry Remote Sens. 58, 1321–1328 (1992).

Lhamon, M. E.

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

M. E. Lhamon, L. G. Hassebrook, “Translation-invariant optical pattern recognition without correlation,” Opt. Eng. 35, 2700–2709 (1996).
[CrossRef]

M. E. Lhamon, “Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems,” Ph.D. dissertation (University of Kentucky, Lexington, Ky., 1997).

Liebowitz, S. A.

D. Casasent, S. A. Liebowitz, A. Mahalanobis, “Parameter selection for iconic and symbolic pattern recognition filters,” in Optical and Digital Pattern Recognition, H. Liu, P. S. Schenker, eds., Proc. SPIE754, 284–303 (1987).
[CrossRef]

Lozano-Perez, T.

W. E. L. Grimson, T. Lozano-Perez, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 469–482 (1987).
[CrossRef]

Mahalanobis, A.

D. Casasent, S. A. Liebowitz, A. Mahalanobis, “Parameter selection for iconic and symbolic pattern recognition filters,” in Optical and Digital Pattern Recognition, H. Liu, P. S. Schenker, eds., Proc. SPIE754, 284–303 (1987).
[CrossRef]

Morandi, C.

E. De Castro, C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 700–703 (1987).
[CrossRef]

Murata, H.

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

Petrou, M.

S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
[CrossRef]

Pochapsky, E.

Rahmati, M.

M. Rahmati, L. G. Hassebrook, “Intensity- and distortion-invariant pattern recognition with complex linear morphology,” Pattern Recogn. 27, 549–568 (1994).
[CrossRef]

L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
[CrossRef]

Roth, P.

R. R. Kallman, P. Roth, T. Turpin, “Correlation results using invariant filters in an acousto-optic correlator,” in Optical Pattern Recognition V, D. P. Casasent, T.-H. Chao, eds., Proc. SPIE2237, 62–73 (1994).
[CrossRef]

Schils, G. F.

Sharer, R. J.

R. J. Sharer, The Ancient Maya, 5th ed. (Stanford U. Press, Stanford, Calif., 1994), p. 324.

Stockman, G.

G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
[CrossRef]

Sweeney, D. W.

Turpin, T.

R. R. Kallman, P. Roth, T. Turpin, “Correlation results using invariant filters in an acousto-optic correlator,” in Optical Pattern Recognition V, D. P. Casasent, T.-H. Chao, eds., Proc. SPIE2237, 62–73 (1994).
[CrossRef]

Van Trees, H. L.

H. L. Van Trees, Detection, Estimation and Modulation Theory (Wiley, New York, 1968), pp. 30 and 258.

Vargese, T.

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

Vijaya Kumar, B. V. K.

L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
[CrossRef]

B. V. K. Vijaya Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
[CrossRef]

L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
[CrossRef]

B. V. K. Vijaya Kumar, E. Pochapsky, “Signal-to-noise ratio considerations in modified matched spatial filters,” J. Opt. Soc. Am. A 3, 777–786 (1986).
[CrossRef]

Wang, M.

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

Wang, Mao

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

Wels, S.

S. Wels, Titanic, Legacy of the New World's Greatest Ocean Liner (Tehabi, Del Mar, Calif., 1997), image on cover.

Ziqing Li, S.

S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
[CrossRef]

ACM (Assoc. Comput. Mach.) Comput. Surv. (2)

L. G. Brown, “A survey of image registration techniques,” ACM (Assoc. Comput. Mach.) Comput. Surv. 24, 325–376 (1992).
[CrossRef]

H. Freeman, “Computer processing of line drawn images,” ACM (Assoc. Comput. Mach.) Comput. Surv. 6, 57–97 (1974).
[CrossRef]

Am. Soc. Photogrammetry Remote Sens. (1)

Liang-Chien Chen, Liang-Hwei Lee, “Progressive generation of control frameworks for image registration,” Am. Soc. Photogrammetry Remote Sens. 58, 1321–1328 (1992).

Appl. Opt. (3)

IEE Proc. E (1)

K. Fukunaga, H. Murata, T. Asano, M. Izumi, “Image registration using an image graph and its application to map matching,” IEE Proc. E 138, 79–84 (1991).

IEEE Trans. Biomed. Eng. (1)

Mao Wang, L. G. Hassebrook, J. Evans, T. Vargese, C. Knapp, “An optimized index of human cardiovascular adaptation to simulated weightlessness,” IEEE Trans. Biomed. Eng. 43, 502–511 (1996).
[CrossRef] [PubMed]

IEEE Trans. Pattern. Anal. Mach. Intell. (3)

W. E. L. Grimson, T. Lozano-Perez, “Localizing overlapping parts by searching the interpretation tree,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 469–482 (1987).
[CrossRef]

E. De Castro, C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-9, 700–703 (1987).
[CrossRef]

G. Stockman, S. Kopstein, S. Benett, “Matching images to models for registration and object detection via clustering,” IEEE Trans. Pattern. Anal. Mach. Intell. PAMI-4, 229–241 (1982).
[CrossRef]

J. Opt. Soc. Am. A (2)

Opt. Eng. (5)

L. G. Hassebrook, M. Rahmati, B. V. K. Vijaya Kumar, “Hybrid composite filter banks for distortion invariant optical pattern recognition,” Opt. Eng. 31, 923–933 (1992).
[CrossRef]

M. E. Lhamon, L. G. Hassebrook, “Translation-invariant optical pattern recognition without correlation,” Opt. Eng. 35, 2700–2709 (1996).
[CrossRef]

L. G. Hassebrook, M. E. Lhamon, M. Wang, J. Chatterjee, “Postprocessing of correlation for orientation estimation,” Opt. Eng. 36, 2710–2718 (1997).
[CrossRef]

L. G. Hassebrook, B. V. K. Vijaya Kumar, L. Hostetler, “Linear phase coefficient composite filters for distortion invariant optical pattern recognition,” Opt. Eng. 29, 1033–1043 (1990).
[CrossRef]

S. Ziqing Li, J. Kittler, M. Petrou, “Automatic registration of aerial photographs and digitized maps,” Opt. Eng. 32, 1213–1221 (1993).
[CrossRef]

Pattern Recogn. (1)

M. Rahmati, L. G. Hassebrook, “Intensity- and distortion-invariant pattern recognition with complex linear morphology,” Pattern Recogn. 27, 549–568 (1994).
[CrossRef]

Other (8)

R. W. Cohn, L. G. Hassebrook, “Representations of fully complex functions on real-time spatial light modulators,” in Optical Pattern Recognition, F. S. Yu, S. Jutamulia, eds. (Cambridge U. Press, New York, 1998), Chap. 15, p. 404.

R. R. Kallman, P. Roth, T. Turpin, “Correlation results using invariant filters in an acousto-optic correlator,” in Optical Pattern Recognition V, D. P. Casasent, T.-H. Chao, eds., Proc. SPIE2237, 62–73 (1994).
[CrossRef]

R. J. Sharer, The Ancient Maya, 5th ed. (Stanford U. Press, Stanford, Calif., 1994), p. 324.

S. Wels, Titanic, Legacy of the New World's Greatest Ocean Liner (Tehabi, Del Mar, Calif., 1997), image on cover.

W. J. Chimitt, L. G. Hassebrook, “Automatic scene reconstruction from partially overlapping images using on line filter design,” in Optical Pattern Recognition IX, D. P. Casasent, T. H. Chao, eds., Proc. SPIE3386, 171–181 (1998).
[CrossRef]

H. L. Van Trees, Detection, Estimation and Modulation Theory (Wiley, New York, 1968), pp. 30 and 258.

M. E. Lhamon, “Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems,” Ph.D. dissertation (University of Kentucky, Lexington, Ky., 1997).

D. Casasent, S. A. Liebowitz, A. Mahalanobis, “Parameter selection for iconic and symbolic pattern recognition filters,” in Optical and Digital Pattern Recognition, H. Liu, P. S. Schenker, eds., Proc. SPIE754, 284–303 (1987).
[CrossRef]

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 (11)

Fig. 1
Fig. 1

POSAS block diagram. The supervisor selects parent and child pairs to be correlated and evaluates quality of registration.

Fig. 2
Fig. 2

Millenium Falcon registration set. Each of the 11 partitions has random rotation and overlap with other partitions.

Fig. 3
Fig. 3

Reassembled scene of Millenium Falcon from registration set in Fig. 2.

Fig. 4
Fig. 4

Control image pair after registration with 12% shared target mass in overlap region.

Fig. 5
Fig. 5

Profile view (i.e., side view of three-dimensional mesh plot) of filter bank response to control imagery. The response is along the vertical axis, and one of two lateral displacements is along the horizontal axis. The second lateral axis is perpendicular to the page. Point A indicates the dominating central response of the filter bank, while point B is the true peak of the partially overlapping regions. Point C indicates the local sidelobe response to the overlapping regions.

Fig. 6
Fig. 6

Profile view of square root of zero-order filter response to control imagery.

Fig. 7
Fig. 7

Profile view of postprocessed filter bank response to control imagery. The postprocessing is the subtraction of the mesh in Fig. 6 from the mesh in Fig. 5, which reveals the location of the peak response of the overlapping regions.

Fig. 8
Fig. 8

Profile view of postprocessed filter bank response to Millenium Falcon partition pair 5 and 8.

Fig. 9
Fig. 9

(a) Rotation autocorrelations of nontraining and training set images and (b) PSR of correlation response to nontraining set images indicating optimum PSR for a training set size of approximately 400.

Fig. 10
Fig. 10

(a) Mayan sculpture image with the use of a single 128×128 sensor image and (b) reconstruction of Mayan sculpture from overlapping partitions by using the same sensor size as that in (a) but with a smaller field of view indicated by the white border of the first partition.

Fig. 11
Fig. 11

(a) Reconstruction of Titanic photograph from 15 partitions with a border around the first partition and (b) reconstruction of aerial photograph provided by Custom Aerial Photography, Inc., 1803 Park Center Drive, Suite 112, Orlando, Florida 32835.

Equations (34)

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

yk(a, b)=xB(a, b)  hA,k(a, b),
hA,k*=n=0N-1xA,n exp-j 2πnN k=XAΦk,
ybank(a, b)=kKbankwk|yk(a, b)|,
Q=sgn(λAA,k-λBA,k)(λAA,k-λBA,k)2λAA,k,
=1d2 ab[αybank(a, b)-βyk=0(a, b)]2,
ypostprocessed(a, b)=αybank(a, b)-βyk=0(a, b).
λAA,k=1N N(xA,0TxA,0)+n=1N-12(N-n)xA,0TxA,n cos2πknN,
λBA,k=1N N(xB,0TxA,0)+n=1N-1(N-n)xB,0TxA,n cos2πknN+m=1N-1(N-m)xB,mTxA,0 cos2πmkN.
wk=λAA,k-λBA,kλAA,k,
L=πR2-2R2 sin-1r2R-rR2-r241/2,
E{Yk|L, H0}
=El=1L[xB(l)hA,k*(l)]|L, H0=El=1LxB(l)n=0N-1xA,n(l)exp-j2πknNL, H0=LNμAμBδ[k],
Var{Yk|L, H0}=E{|Yk|2|L, H0}-(LNμaμb)2δ[k],
E{|Yk|2|L, H0}=El=1LxB(l)hA,k*(l)2L, H0.
var{Yk|L, H0}=LN{σA2(σB2+μB2)+NμA2σB2δ[k]}.
dev{Yk|L,H0}=(LN{σA2(σB2+μB2)+NμA2σB2δ[k]})1/2.
dev(k=0)mean(k=0)={LN[σA2(σB2+μB2)+NμA2σB2]}1/2LNμAμB.
E{Yk|L, H1(100%)}
=El=1Lxn=02(l)|L, H1(100%)+El=1Lxn=0(l)n=1N-1xn(l)×exp-j2πknNL, H1(100%)=L(σ2+μ2)+Lμ2(Nδ[k]-1).
Δ=L(σ2+μ2)+Lμ2(Nδ[k]-1)LNμAμBδ[k]-1.
E{targetresponse}E{sidelobeheight}at target peak location
=LσA2{LN[σA2(σB2+μB2)]}1/2=2.49.
PSRwc(N)E{|Yk>0||N, Hwc}Dev{Yk>0|N, Hwc},
|ywc,k|=2n=0N/2-1R(Θwc(n, m))×expjπkNcosπkN (2N+1),
λwc,k=E{|ywc,k|}|ywc,k|
Dev{yk>0|L, Hwc}
=L(σ2+μ2)m=1Nn=1NR(ΘΔ(m-n, N))L-μ2
×expj2π(m-n)kN.
Dev{yk>0|L, H0}
=L(σ2+μ2)m=1NR(ΘΔ(m-n, N))L-μ2
×cos2πmkN.
gn=kKbankyps(k)exp-j2πknN
RAB={a, b; uA(a, b)uB(a(a), b(b))=1}
Γ={a,b}RABxA(a, b)xB(a(a), b(b)){a,b}RABxA2(a, b){a,b}RABxB2(a(a), b(b))1/2,

Metrics