Abstract

Different types of cells are recognized from their noisy images by use of a hybrid recognition system that consists of a learning principal-component analyzer and an image-classifier network. The inputs to the feed-forward backpropagation classifier are the first 15 principal components of the 10 × 10 pixel image to be classified. The classifier was trained with clear images of cells in metaphase, unburst cells, and other erroneous patterns. Experimental results show that the recognition system is robust to image scaling and rotation, as well as to image noise. Cell recognition is demonstrated for images that are corrupted with additive Gaussian noise, impulse noise, and quantization errors. We compare the performance of the hybrid recognition system with that of a conventional three-layer feed-forward backpropagation network that uses the raw image directly as input.

© 1998 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. Soriano and C. Saloma, “Cell classification by a learning principal components analyzer and a backpropagation neural network,” Bioimaging 3, 168–175 (1995).
    [CrossRef]
  2. H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).
  3. B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).
  4. R. Gonzalez and R. Woods, Digital Image Processing (Addison-Wesley, New York, 1993).
  5. T. Masters, Signal and Image Processing With Neural Networks (Wiley, New York, 1993).
  6. S. Haykin, Neural Network—A Comprehensive Foundation (Macmillan, New York, 1994).
  7. M. McCord Nelson, and W. Illington, A Practical Guide to Neural Nets (Addison-Wesley, Reading, Mass., 1991).
  8. C. Bishop, Neural Networks for Statistical Pattern Recognition (Oxford U. Press, Oxford, 1994).
  9. T. Watkin and A. Rau, “The statistical mechanics of learning a rule,” Rev. Mod. Phys. 65, 499–556 (1994).
    [CrossRef]
  10. A. Jain and J. Mao, “Guest editorial: special issue on artificial neural networks and statistical pattern recognition,” IEEE Trans. Neural Networks 8, 1–3 (1997).
    [CrossRef]
  11. J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
    [CrossRef]
  12. L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.
  13. Y. Qi and B. Hunt, “Signature verification using global and grid features,” Patt. Recog. 27, 1621–1629 (1994).
    [CrossRef]
  14. D. Burton, “Text-dependent speaker verification using vector quantization source coding,” IEEE Trans. Acoust. Speech Signal Process. ASSP-35, 133–140 (1987).
    [CrossRef]
  15. F. Tsung and G. Cottrell, “Learning in recurrent finite difference networks,” Int. J. Neural Sys. 6, 249–255 (1995).
    [CrossRef]
  16. G. Cottrell and J. Metcalfe “EMPATH: face, emotion and gender recognition using holons,” in Vol. 3 of Advances in Neural Information Processing Systems Series (Morgan Kaufmann, San Mateo, Calif., 1991), pp. 564–571.
  17. S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
    [CrossRef]
  18. D. Beymer and T. Poggio, “Image representations for visual learning,” Science 272, 1905–1909 (1996).
    [CrossRef] [PubMed]
  19. R. Chellapa, C. Wilson, and S. Sirohey, “Human and machine recognition of faces,” Proc. IEEE 83, 705–740 (1995).
    [CrossRef]
  20. I. Cox, J. Ghosn, and P. Yianilos, “Feature-based face recognition using mixture–distance,” in Computer Vision and Pattern Recognition (IEEE Press, Piscataway, N.J., 1996).
  21. D. Rosenthal and L. Mango, “Applications of neural networks for interactive diagnosis of anatomic pathology specimens,” in Compendium on the Computerized Cytology and Histology Laboratory, Tutorials of Cytology, G. Weid, P. Bartels, D. Rosenthal, and U. Schenck, eds. (Karger, Chicago, 1994), pp. 173–184.
  22. M. Astion and P. Wilding, “The application of backpropagation neural networks to problems in pathology,” Arch. Pathol. Lab. Med. 116, 995–1001 (1992).
    [PubMed]
  23. S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).
  24. C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).
  25. M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
    [CrossRef] [PubMed]
  26. A. Dawson, R. Austin, and D. Weinberg, “Nuclear grading of breast carcinoma by image analysis: classification by multivariate and neural network analysis,” Am. J. Clin. Pathol. (Suppl. 4) 95, 529–530.
  27. L. Mango, “Deducing false negatives in clinical practice: the role of neural network technology,” Am. J. Obstetr. Gynecol. 175, 1114–1119 (1996).
    [CrossRef]
  28. J. Terrillon, “Image preprocessing for rotation-invariant pattern recognition in the presence of signal-dependent noise,” Appl. Opt. 35, 1879–1893 (1996).
    [CrossRef] [PubMed]
  29. K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed. (Macmillan, New York, 1990).
  30. K. Fukunaga and J. Young, “Pattern recognition and neural engineering,” in Neural Networks, Concepts, Applications and Implementations, P. Antognetti and V. Milutinovic, eds. (Prentice Hall, EngleWood Cliffs, N.J., 1991), Vol. 1, pp. 10–33.
  31. L. Sirovich and M. Kirby, “Low-dimensional procedure for the characterization of human faces,” J. Opt. Soc. Am. A 4, 519–524 (1987).
    [CrossRef] [PubMed]
  32. L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
    [CrossRef]
  33. T. Sanger, “Optimal unsupervised learning in a single-layer linear feed forward neural network,” Neural Networks 2, 459–473 (1989).
    [CrossRef]
  34. J. Tou and R. Gonzalez, Pattern Recognition Principles (Addison-Wesley, London, 1974).
  35. A. Papoulis, Probability, Random Variables, and Stochastic Processes, 2nd ed. (McGraw-Hill, New York, 1984).
  36. G. Parry, “Speckle patterns in partially coherent light,” in Laser Speckle and Related Phenomena, Vol. 9 of Topics in Applied Physics Series (Springer-Verlag, Berlin, 1984).
  37. C. Saloma, S. Kawata, and S. Minami, “Laser diode microscope that generates weakly speckled images,” Opt. Lett. 15, 203–205 (1990).
    [CrossRef] [PubMed]
  38. P. Chavel, “Optical noise and temporal coherence,” J. Opt. Soc. Am. 70, 935–1012 (1980).
    [CrossRef]
  39. J. Chamberlain, The Principles of Interferometric Spectroscopy (Wiley, New York, 1979), Chap. 9.
  40. V. Daria, O. Nakamura, C. Palmes-Saloma, K. Fujita, C. Saloma, H. Kondoh, and S. Kawata, “Long-depth imaging of turbid biological samples by two-photon fluorescence microscopy,” paper presented at the Nineteenth Meeting of the Japan Society for Laser Microscopy, Nagoya, Japan, 8–10 May 1997.
  41. S. Inoue, Video Microscopy (Plenum, New York, 1986).
  42. J. Proakis and D. Manolakis, Digital Signal Processing—Principles, Algorithm, and Applications, 2nd ed. (Macmillan, New York, 1992), pp. 41–43.
  43. L. Levi, Applied Optics—A Guide to Optical System Design (Wiley, New York, 1968), Vol. 1, pp. 152–154.
  44. W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

1997 (3)

A. Jain and J. Mao, “Guest editorial: special issue on artificial neural networks and statistical pattern recognition,” IEEE Trans. Neural Networks 8, 1–3 (1997).
[CrossRef]

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).

1996 (4)

M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
[CrossRef] [PubMed]

L. Mango, “Deducing false negatives in clinical practice: the role of neural network technology,” Am. J. Obstetr. Gynecol. 175, 1114–1119 (1996).
[CrossRef]

D. Beymer and T. Poggio, “Image representations for visual learning,” Science 272, 1905–1909 (1996).
[CrossRef] [PubMed]

J. Terrillon, “Image preprocessing for rotation-invariant pattern recognition in the presence of signal-dependent noise,” Appl. Opt. 35, 1879–1893 (1996).
[CrossRef] [PubMed]

1995 (3)

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

M. Soriano and C. Saloma, “Cell classification by a learning principal components analyzer and a backpropagation neural network,” Bioimaging 3, 168–175 (1995).
[CrossRef]

F. Tsung and G. Cottrell, “Learning in recurrent finite difference networks,” Int. J. Neural Sys. 6, 249–255 (1995).
[CrossRef]

1994 (4)

S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).

T. Watkin and A. Rau, “The statistical mechanics of learning a rule,” Rev. Mod. Phys. 65, 499–556 (1994).
[CrossRef]

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Y. Qi and B. Hunt, “Signature verification using global and grid features,” Patt. Recog. 27, 1621–1629 (1994).
[CrossRef]

1992 (1)

M. Astion and P. Wilding, “The application of backpropagation neural networks to problems in pathology,” Arch. Pathol. Lab. Med. 116, 995–1001 (1992).
[PubMed]

1990 (2)

L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
[CrossRef]

C. Saloma, S. Kawata, and S. Minami, “Laser diode microscope that generates weakly speckled images,” Opt. Lett. 15, 203–205 (1990).
[CrossRef] [PubMed]

1989 (1)

T. Sanger, “Optimal unsupervised learning in a single-layer linear feed forward neural network,” Neural Networks 2, 459–473 (1989).
[CrossRef]

1987 (2)

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

D. Burton, “Text-dependent speaker verification using vector quantization source coding,” IEEE Trans. Acoust. Speech Signal Process. ASSP-35, 133–140 (1987).
[CrossRef]

1980 (1)

Alberts, B.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

An, C.

C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).

Arai, F.

S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).

Astion, M.

M. Astion and P. Wilding, “The application of backpropagation neural networks to problems in pathology,” Arch. Pathol. Lab. Med. 116, 995–1001 (1992).
[PubMed]

Back, A.

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

Baltimore, D.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Berk, A.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Beymer, D.

D. Beymer and T. Poggio, “Image representations for visual learning,” Science 272, 1905–1909 (1996).
[CrossRef] [PubMed]

Bishop, C.

C. Bishop, Neural Networks for Statistical Pattern Recognition (Oxford U. Press, Oxford, 1994).

Blue, J.

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Bottou, L.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Bray, D.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

Brickley, M.

M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
[CrossRef] [PubMed]

Burton, D.

D. Burton, “Text-dependent speaker verification using vector quantization source coding,” IEEE Trans. Acoust. Speech Signal Process. ASSP-35, 133–140 (1987).
[CrossRef]

Candela, G.

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Chamberlain, J.

J. Chamberlain, The Principles of Interferometric Spectroscopy (Wiley, New York, 1979), Chap. 9.

Chavel, P.

Chellapa, R.

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

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Cortes, C.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Cottrell, G.

F. Tsung and G. Cottrell, “Learning in recurrent finite difference networks,” Int. J. Neural Sys. 6, 249–255 (1995).
[CrossRef]

Coupe, J.

M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
[CrossRef] [PubMed]

Cox, I.

I. Cox, J. Ghosn, and P. Yianilos, “Feature-based face recognition using mixture–distance,” in Computer Vision and Pattern Recognition (IEEE Press, Piscataway, N.J., 1996).

Darnell, J.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Denker, J.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Drucker, H.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Flannery, B.

W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

Fukuda, T.

S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).

Fukunaga, K.

K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed. (Macmillan, New York, 1990).

K. Fukunaga and J. Young, “Pattern recognition and neural engineering,” in Neural Networks, Concepts, Applications and Implementations, P. Antognetti and V. Milutinovic, eds. (Prentice Hall, EngleWood Cliffs, N.J., 1991), Vol. 1, pp. 10–33.

Ghosn, J.

I. Cox, J. Ghosn, and P. Yianilos, “Feature-based face recognition using mixture–distance,” in Computer Vision and Pattern Recognition (IEEE Press, Piscataway, N.J., 1996).

Giles, C. Lee

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

Gonzalez, R.

J. Tou and R. Gonzalez, Pattern Recognition Principles (Addison-Wesley, London, 1974).

R. Gonzalez and R. Woods, Digital Image Processing (Addison-Wesley, New York, 1993).

Grother, P.

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Gupta, L.

L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
[CrossRef]

Guyon, I.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Haykin, S.

S. Haykin, Neural Network—A Comprehensive Foundation (Macmillan, New York, 1994).

Hunt, B.

Y. Qi and B. Hunt, “Signature verification using global and grid features,” Patt. Recog. 27, 1621–1629 (1994).
[CrossRef]

Illington, W.

M. McCord Nelson, and W. Illington, A Practical Guide to Neural Nets (Addison-Wesley, Reading, Mass., 1991).

Inoue, S.

S. Inoue, Video Microscopy (Plenum, New York, 1986).

Jackel, L.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Jain, A.

A. Jain and J. Mao, “Guest editorial: special issue on artificial neural networks and statistical pattern recognition,” IEEE Trans. Neural Networks 8, 1–3 (1997).
[CrossRef]

Kawata, S.

Kirby, M.

Lawrence, S.

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

Le Cun, Y.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Levi, L.

L. Levi, Applied Optics—A Guide to Optical System Design (Wiley, New York, 1968), Vol. 1, pp. 152–154.

Lewis, J.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

Lodish, H.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Mango, L.

L. Mango, “Deducing false negatives in clinical practice: the role of neural network technology,” Am. J. Obstetr. Gynecol. 175, 1114–1119 (1996).
[CrossRef]

D. Rosenthal and L. Mango, “Applications of neural networks for interactive diagnosis of anatomic pathology specimens,” in Compendium on the Computerized Cytology and Histology Laboratory, Tutorials of Cytology, G. Weid, P. Bartels, D. Rosenthal, and U. Schenck, eds. (Karger, Chicago, 1994), pp. 173–184.

Manolakis, D.

J. Proakis and D. Manolakis, Digital Signal Processing—Principles, Algorithm, and Applications, 2nd ed. (Macmillan, New York, 1992), pp. 41–43.

Mao, J.

A. Jain and J. Mao, “Guest editorial: special issue on artificial neural networks and statistical pattern recognition,” IEEE Trans. Neural Networks 8, 1–3 (1997).
[CrossRef]

Marchevsky, A.

C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).

Masters, T.

T. Masters, Signal and Image Processing With Neural Networks (Wiley, New York, 1993).

Matsudaira, P.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Minami, S.

Mohammed, R.

L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
[CrossRef]

Muller, U.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Nelson, M. McCord

M. McCord Nelson, and W. Illington, A Practical Guide to Neural Nets (Addison-Wesley, Reading, Mass., 1991).

Papoulis, A.

A. Papoulis, Probability, Random Variables, and Stochastic Processes, 2nd ed. (McGraw-Hill, New York, 1984).

Parry, G.

G. Parry, “Speckle patterns in partially coherent light,” in Laser Speckle and Related Phenomena, Vol. 9 of Topics in Applied Physics Series (Springer-Verlag, Berlin, 1984).

Petrovic, L.

C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).

Poggio, T.

D. Beymer and T. Poggio, “Image representations for visual learning,” Science 272, 1905–1909 (1996).
[CrossRef] [PubMed]

Press, W.

W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

Proakis, J.

J. Proakis and D. Manolakis, Digital Signal Processing—Principles, Algorithm, and Applications, 2nd ed. (Macmillan, New York, 1992), pp. 41–43.

Qi, Y.

Y. Qi and B. Hunt, “Signature verification using global and grid features,” Patt. Recog. 27, 1621–1629 (1994).
[CrossRef]

Raff, M.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

Rau, A.

T. Watkin and A. Rau, “The statistical mechanics of learning a rule,” Rev. Mod. Phys. 65, 499–556 (1994).
[CrossRef]

Roberts, K.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

Rosenthal, D.

D. Rosenthal and L. Mango, “Applications of neural networks for interactive diagnosis of anatomic pathology specimens,” in Compendium on the Computerized Cytology and Histology Laboratory, Tutorials of Cytology, G. Weid, P. Bartels, D. Rosenthal, and U. Schenck, eds. (Karger, Chicago, 1994), pp. 173–184.

Sackinger, E.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Saloma, C.

M. Soriano and C. Saloma, “Cell classification by a learning principal components analyzer and a backpropagation neural network,” Bioimaging 3, 168–175 (1995).
[CrossRef]

C. Saloma, S. Kawata, and S. Minami, “Laser diode microscope that generates weakly speckled images,” Opt. Lett. 15, 203–205 (1990).
[CrossRef] [PubMed]

Sanger, T.

T. Sanger, “Optimal unsupervised learning in a single-layer linear feed forward neural network,” Neural Networks 2, 459–473 (1989).
[CrossRef]

Shepherd, J.

M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
[CrossRef] [PubMed]

Shiotani, S.

S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).

Simard, P.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Sirohey, S.

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

Sirovich, L.

Soriano, M.

M. Soriano and C. Saloma, “Cell classification by a learning principal components analyzer and a backpropagation neural network,” Bioimaging 3, 168–175 (1995).
[CrossRef]

Tammana, R.

L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
[CrossRef]

Terrillon, J.

Teukolsky, S.

W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

Tou, J.

J. Tou and R. Gonzalez, Pattern Recognition Principles (Addison-Wesley, London, 1974).

Tsoi, A. C.

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

Tsung, F.

F. Tsung and G. Cottrell, “Learning in recurrent finite difference networks,” Int. J. Neural Sys. 6, 249–255 (1995).
[CrossRef]

Vapnik, V.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

Vetterling, W.

W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

Watkin, T.

T. Watkin and A. Rau, “The statistical mechanics of learning a rule,” Rev. Mod. Phys. 65, 499–556 (1994).
[CrossRef]

Watson, J.

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

Wilding, P.

M. Astion and P. Wilding, “The application of backpropagation neural networks to problems in pathology,” Arch. Pathol. Lab. Med. 116, 995–1001 (1992).
[PubMed]

Wilson, C.

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

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Woods, R.

R. Gonzalez and R. Woods, Digital Image Processing (Addison-Wesley, New York, 1993).

Yianilos, P.

I. Cox, J. Ghosn, and P. Yianilos, “Feature-based face recognition using mixture–distance,” in Computer Vision and Pattern Recognition (IEEE Press, Piscataway, N.J., 1996).

Young, J.

K. Fukunaga and J. Young, “Pattern recognition and neural engineering,” in Neural Networks, Concepts, Applications and Implementations, P. Antognetti and V. Milutinovic, eds. (Prentice Hall, EngleWood Cliffs, N.J., 1991), Vol. 1, pp. 10–33.

Zipursky, S.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

Am. J. Obstetr. Gynecol. (1)

L. Mango, “Deducing false negatives in clinical practice: the role of neural network technology,” Am. J. Obstetr. Gynecol. 175, 1114–1119 (1996).
[CrossRef]

Appl. Opt. (1)

Arch. Pathol. Lab. Med. (1)

M. Astion and P. Wilding, “The application of backpropagation neural networks to problems in pathology,” Arch. Pathol. Lab. Med. 116, 995–1001 (1992).
[PubMed]

Bioimaging (1)

M. Soriano and C. Saloma, “Cell classification by a learning principal components analyzer and a backpropagation neural network,” Bioimaging 3, 168–175 (1995).
[CrossRef]

Hepatocell Carcin. (1)

C. An, L. Petrovic, and A. Marchevsky, “The application of image analysis and neural network technology to the study of large cell liver cells,” Hepatocell Carcin. 26, 1224–2230 (1997).

IEEE Trans. Acoust. Speech Signal Process. (1)

D. Burton, “Text-dependent speaker verification using vector quantization source coding,” IEEE Trans. Acoust. Speech Signal Process. ASSP-35, 133–140 (1987).
[CrossRef]

IEEE Trans. Neural Networks (2)

S. Lawrence, C. Lee Giles, A. C. Tsoi, and A. Back, “Face recognition: a convolutional neural-network approach,” IEEE Trans. Neural Networks 8, 98–113 (1997).
[CrossRef]

A. Jain and J. Mao, “Guest editorial: special issue on artificial neural networks and statistical pattern recognition,” IEEE Trans. Neural Networks 8, 1–3 (1997).
[CrossRef]

Int. J. Neural Sys. (1)

F. Tsung and G. Cottrell, “Learning in recurrent finite difference networks,” Int. J. Neural Sys. 6, 249–255 (1995).
[CrossRef]

J. Opt. Soc. Am. (1)

J. Opt. Soc. Am. A (1)

J. Oral Pathol. Med. (1)

M. Brickley, J. Coupe, and J. Shepherd, “Performance of a computer-simulated neural network trained to categorize normal, premalignant and malignant oral smears,” J. Oral Pathol. Med. 25, 424–430 (1996).
[CrossRef] [PubMed]

JSME Int. J. Ser. C (1)

S. Shiotani, T. Fukuda, and F. Arai, “Cell recognition by image processing (recognition of dead or living plant cells by neural network),” JSME Int. J. Ser. C 371, 233–240 (1994).

Neural Networks (1)

T. Sanger, “Optimal unsupervised learning in a single-layer linear feed forward neural network,” Neural Networks 2, 459–473 (1989).
[CrossRef]

Opt. Lett. (1)

Patt. Recog. (2)

J. Blue, G. Candela, P. Grother, R. Chellapa, and C. Wilson, “Evaluation of pattern classifiers for fingerprint and OCR applications,” Patt. Recog. 27, 485–501 (1994).
[CrossRef]

Y. Qi and B. Hunt, “Signature verification using global and grid features,” Patt. Recog. 27, 1621–1629 (1994).
[CrossRef]

Pattern Recog. (1)

L. Gupta, R. Mohammed, and R. Tammana, “A neural network approach to robust shape classification,” Pattern Recog. 23, 563–568 (1990).
[CrossRef]

Proc. IEEE (1)

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

Rev. Mod. Phys. (1)

T. Watkin and A. Rau, “The statistical mechanics of learning a rule,” Rev. Mod. Phys. 65, 499–556 (1994).
[CrossRef]

Science (1)

D. Beymer and T. Poggio, “Image representations for visual learning,” Science 272, 1905–1909 (1996).
[CrossRef] [PubMed]

Other (23)

G. Cottrell and J. Metcalfe “EMPATH: face, emotion and gender recognition using holons,” in Vol. 3 of Advances in Neural Information Processing Systems Series (Morgan Kaufmann, San Mateo, Calif., 1991), pp. 564–571.

L. Bottou, C. Cortes, J. Denker, H. Drucker, I. Guyon, L. Jackel, Y. Le Cun, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Comparison of classifier methods: a case study in handwritten digit recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE Comput. Soc. Press, Los Alamitos, Calif., 1994), Vol. 2, pp. 77–82.

H. Lodish, D. Baltimore, A. Berk, S. Zipursky, P. Matsudaira, and J. Darnell, Molecular Cell Biology (Scientific American, New York, 1995).

B. Alberts, D. Bray, J. Lewis, M. Raff, K. Roberts, and J. Watson, Molecular Biology of the Cell (Garland, New York, 1989).

R. Gonzalez and R. Woods, Digital Image Processing (Addison-Wesley, New York, 1993).

T. Masters, Signal and Image Processing With Neural Networks (Wiley, New York, 1993).

S. Haykin, Neural Network—A Comprehensive Foundation (Macmillan, New York, 1994).

M. McCord Nelson, and W. Illington, A Practical Guide to Neural Nets (Addison-Wesley, Reading, Mass., 1991).

C. Bishop, Neural Networks for Statistical Pattern Recognition (Oxford U. Press, Oxford, 1994).

I. Cox, J. Ghosn, and P. Yianilos, “Feature-based face recognition using mixture–distance,” in Computer Vision and Pattern Recognition (IEEE Press, Piscataway, N.J., 1996).

D. Rosenthal and L. Mango, “Applications of neural networks for interactive diagnosis of anatomic pathology specimens,” in Compendium on the Computerized Cytology and Histology Laboratory, Tutorials of Cytology, G. Weid, P. Bartels, D. Rosenthal, and U. Schenck, eds. (Karger, Chicago, 1994), pp. 173–184.

A. Dawson, R. Austin, and D. Weinberg, “Nuclear grading of breast carcinoma by image analysis: classification by multivariate and neural network analysis,” Am. J. Clin. Pathol. (Suppl. 4) 95, 529–530.

J. Tou and R. Gonzalez, Pattern Recognition Principles (Addison-Wesley, London, 1974).

A. Papoulis, Probability, Random Variables, and Stochastic Processes, 2nd ed. (McGraw-Hill, New York, 1984).

G. Parry, “Speckle patterns in partially coherent light,” in Laser Speckle and Related Phenomena, Vol. 9 of Topics in Applied Physics Series (Springer-Verlag, Berlin, 1984).

J. Chamberlain, The Principles of Interferometric Spectroscopy (Wiley, New York, 1979), Chap. 9.

V. Daria, O. Nakamura, C. Palmes-Saloma, K. Fujita, C. Saloma, H. Kondoh, and S. Kawata, “Long-depth imaging of turbid biological samples by two-photon fluorescence microscopy,” paper presented at the Nineteenth Meeting of the Japan Society for Laser Microscopy, Nagoya, Japan, 8–10 May 1997.

S. Inoue, Video Microscopy (Plenum, New York, 1986).

J. Proakis and D. Manolakis, Digital Signal Processing—Principles, Algorithm, and Applications, 2nd ed. (Macmillan, New York, 1992), pp. 41–43.

L. Levi, Applied Optics—A Guide to Optical System Design (Wiley, New York, 1968), Vol. 1, pp. 152–154.

W. Press, S. Teukolsky, W. Vetterling, and B. Flannery, Numerical Recipes in C—The Art of Scientific Computing, 2nd ed. (Cambridge U. Press, New York, 1992).

K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd ed. (Macmillan, New York, 1990).

K. Fukunaga and J. Young, “Pattern recognition and neural engineering,” in Neural Networks, Concepts, Applications and Implementations, P. Antognetti and V. Milutinovic, eds. (Prentice Hall, EngleWood Cliffs, N.J., 1991), Vol. 1, pp. 10–33.

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

PCAN + NN: The M × M pixel image to be classified is represented by the N = M 2 component vector X = {X 1, X 2, … , X N } T . The first P PC projections of PCAN are used as inputs to the backpropagation classifier NN, which has three outputs (O = 3) corresponding to the three types of images to be classified.

Fig. 2
Fig. 2

Collage of the 8-bit images that were used for network training: (a) Metaphase spreads. (b) Unburst cells. (c) Typical extraneous images. Each image is considered noiseless and has a size of 10 × 10 pixels.

Fig. 3
Fig. 3

Error E versus the iteration number q for different values of H for the PCAN + NN (a) with P = 15, and (b) different values of P at H = 20. The learning ability of the PCAN + NN is compared with a direct image-input (100 inputs, 20 hidden units, 3 outputs) BPN. All networks were trained with the same set of images.

Fig. 4
Fig. 4

Projection ΔX · e1 of error ΔX along the principal axis in the direction of e1. Unless i and e1 are parallel to each other, |ΔX · e1| < ΔX.

Fig. 5
Fig. 5

Effect of noise on 8-bit metaphase images: (a) Additive Gaussian noise with σ2 = 30. (b) Impulse noise (Poisson variate) with σ2 = 30. (c) Impulse noise with gain g = 2.0. (d) Impulse noise with a bias of 30.

Fig. 6
Fig. 6

Noise-filtering effect obtained by reconstruction of a noisy image in terms of the first 15 PC’s derived from the clear images in the training set: (a) Clear test images of cells. (b) Corresponding images with additive Gaussian noise (σ2 = 20). (c) Reconstruction of (b).

Fig. 7
Fig. 7

Q plotted versus σ2: The image contains additive Gaussian noise and is reconstructed in terms of the first 15 PC’s derived from the clear images in the training set. Each point represents the average over 500 trials. (a) Noise images generated by use of the training set (30 images for each cell type). (b) Noise images generated by use of the test set (41 images for each cell type).

Fig. 8
Fig. 8

R plotted versus σ2 for the PCAN + NN (filled squares) and the BPN (open squares) for images corrupted with (a) additive Gaussian noise and (b) impulse noise. Each point represents the average over 500 trials.

Fig. 9
Fig. 9

R plotted versus σ2 for the PCAN + NN (filled squares) and the BPN (open squares) when the images are given a bias (offset). The original images in the training and the test sets correspond to a bias of zero. Each point represents the average over 500 trials.

Fig. 10
Fig. 10

Training set: Recognition performance of the PCAN + NN (filled circles) and the BPN (open circles) when the image with additive Gaussian noise is gain adjusted before it is identified: (a) R (g, σ2) plots and (b) SD (g, σ2) plots. Each R (g, σ2) point represents the average over 500 trials.

Fig. 11
Fig. 11

Test set: Recognition performance of the PCAN + NN (filled circles) and the BPN (open circles) when the image with additive Gaussian noise is gain adjusted before it is identified: (a) R (g, σ2) plots and (b) SD (g, σ2) plots. Each R (g, σ2) point represents the average over 500 trials.

Tables (2)

Tables Icon

Table 1 Recognition Rate of the PCAN + NN and the BPN for Rotated Images in the Training Set

Tables Icon

Table 2 Recognition Rate of the PCAN + NN and the BPN for Rotated Images in the Test Set

Equations (2)

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

X = | X | e 1 + 0 e 2 = | X | e 1 ,
X r = X · e 1 e 1 + X · e 2 e 2 + + X · e m e m ,

Metrics