Abstract

The Mel frequency cepstral coefficient (MFCC) model, which is widely used in speech detection and recognition, is introduced to extract features from hyperspectral image data. The similarities and differences between speech signals and spectral image data are compared and analyzed. The standard MFCC model is then improved to suit the characteristics of spectral image data by reintroducing the discarded phase information. Finally, the proposed model is applied to two real hyperspectral subimages. Experimental results show that the MFCC feature is sensitive and discriminative among reflectance spectra. It can be used as an effective feature extraction method for hyperspectral image classification.

© 2010 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. G. A. Shaw and H. Burke, “Spectral imaging for remote sensing,” Lincoln Lab. J. 14, 3–28 (2003).
  2. G. F. Hughes, “On the mean accuracy of statistical pattern recognizers,” IEEE Trans. Inf. Theory 14, 55–63 (1968).
    [CrossRef]
  3. P. F. Chen and C. T. Tho, “Hyperspectral imagery classification using a backpropagation neural network,” in 1994 IEEE International Conference on Neural Networks (IEEE, 1994), pp. 2942–2947.
    [CrossRef]
  4. S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
    [CrossRef]
  5. F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
    [CrossRef]
  6. G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
    [CrossRef]
  7. A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).
  8. T. K. Moon, “The expectation-maximization algorithm,” IEEE Signal Process. Mag. 13, 47–60 (1996).
    [CrossRef]
  9. S. B. Serpico and L. Bruzzone, “A new search algorithm for feature selection in hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 39, 1360–1367 (2001).
    [CrossRef]
  10. S. B. Serpico and G. Moser, “Extraction of spectral channels from hyperspectral images for classification purposes,” IEEE Trans. Geosci. Remote Sens. 45, 484–495 (2007).
    [CrossRef]
  11. S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
    [CrossRef]
  12. L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
    [CrossRef]
  13. A. R. Webb, Statistical Pattern Recognition (Wiley, 2002).
    [CrossRef]
  14. B. Javidi, Image Recognition and Classification Algorithms, Systems, and Applications (Marcel Dekker, 2002).
    [CrossRef]
  15. Q. Du and H. Ren, “Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery,” Pattern Recogn. 36, 1–12 (2003).
    [CrossRef]
  16. R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).
  17. B. C. Kuo and D. A. Landgrebe, “Nonparametric weighted feature extraction for classification,” IEEE Trans. Geosci. Remote Sens. 42, 1096–1105 (2004).
    [CrossRef]
  18. S. B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980).
    [CrossRef]
  19. L. Rabiner and B. Juang, Fundamentals of Speech Recognition (Prentice-Hall, 1993).
  20. S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).
  21. T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.
  22. J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

2007

S. B. Serpico and G. Moser, “Extraction of spectral channels from hyperspectral images for classification purposes,” IEEE Trans. Geosci. Remote Sens. 45, 484–495 (2007).
[CrossRef]

2006

S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).

2005

T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

2004

B. C. Kuo and D. A. Landgrebe, “Nonparametric weighted feature extraction for classification,” IEEE Trans. Geosci. Remote Sens. 42, 1096–1105 (2004).
[CrossRef]

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

2003

G. A. Shaw and H. Burke, “Spectral imaging for remote sensing,” Lincoln Lab. J. 14, 3–28 (2003).

Q. Du and H. Ren, “Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery,” Pattern Recogn. 36, 1–12 (2003).
[CrossRef]

2002

L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
[CrossRef]

A. R. Webb, Statistical Pattern Recognition (Wiley, 2002).
[CrossRef]

B. Javidi, Image Recognition and Classification Algorithms, Systems, and Applications (Marcel Dekker, 2002).
[CrossRef]

2001

S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
[CrossRef]

R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).

S. B. Serpico and L. Bruzzone, “A new search algorithm for feature selection in hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 39, 1360–1367 (2001).
[CrossRef]

1997

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

1996

T. K. Moon, “The expectation-maximization algorithm,” IEEE Signal Process. Mag. 13, 47–60 (1996).
[CrossRef]

1994

P. F. Chen and C. T. Tho, “Hyperspectral imagery classification using a backpropagation neural network,” in 1994 IEEE International Conference on Neural Networks (IEEE, 1994), pp. 2942–2947.
[CrossRef]

1993

L. Rabiner and B. Juang, Fundamentals of Speech Recognition (Prentice-Hall, 1993).

1980

S. B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980).
[CrossRef]

1977

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).

1968

G. F. Hughes, “On the mean accuracy of statistical pattern recognizers,” IEEE Trans. Inf. Theory 14, 55–63 (1968).
[CrossRef]

Ahmad, Z.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

Alonso-Chordá, L.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Ariyaeeinia, A.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

B., S. B.

S. B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980).
[CrossRef]

Barhen, J.

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Bruce, L. M.

L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
[CrossRef]

Bruzzone, L.

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

S. B. Serpico and L. Bruzzone, “A new search algorithm for feature selection in hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 39, 1360–1367 (2001).
[CrossRef]

Burke, H.

G. A. Shaw and H. Burke, “Spectral imaging for remote sensing,” Lincoln Lab. J. 14, 3–28 (2003).

Calpe-Maravilla, J.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Camps-Valls, G.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Chen, P. F.

P. F. Chen and C. T. Tho, “Hyperspectral imagery classification using a backpropagation neural network,” in 1994 IEEE International Conference on Neural Networks (IEEE, 1994), pp. 2942–2947.
[CrossRef]

Crawford, M. M.

S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
[CrossRef]

Dempster, A. P.

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).

Du, Q.

Q. Du and H. Ren, “Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery,” Pattern Recogn. 36, 1–12 (2003).
[CrossRef]

Duda, R. O.

R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).

Fakotakis, N.

T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.

Ganchev, T.

T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.

Gat, N.

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Ghosh, J.

S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
[CrossRef]

Gómez-Chova, L.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Hart, P. E.

R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).

Hughes, G. F.

G. F. Hughes, “On the mean accuracy of statistical pattern recognizers,” IEEE Trans. Inf. Theory 14, 55–63 (1968).
[CrossRef]

Javidi, B.

B. Javidi, Image Recognition and Classification Algorithms, Systems, and Applications (Marcel Dekker, 2002).
[CrossRef]

Juang, B.

L. Rabiner and B. Juang, Fundamentals of Speech Recognition (Prentice-Hall, 1993).

Koger, C. H.

L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
[CrossRef]

Kokkinakis, G.

T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.

Kumar, S.

S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
[CrossRef]

Kuo, B. C.

B. C. Kuo and D. A. Landgrebe, “Nonparametric weighted feature extraction for classification,” IEEE Trans. Geosci. Remote Sens. 42, 1096–1105 (2004).
[CrossRef]

Laird, N. M.

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).

Landgrebe, D. A.

B. C. Kuo and D. A. Landgrebe, “Nonparametric weighted feature extraction for classification,” IEEE Trans. Geosci. Remote Sens. 42, 1096–1105 (2004).
[CrossRef]

Lehn-Schiøler, T.

S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).

Li, J.

L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
[CrossRef]

Martín-Guerrero, J. D.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Melgani, F.

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

Mermelstein, P.

S. B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980).
[CrossRef]

Moon, T. K.

T. K. Moon, “The expectation-maximization algorithm,” IEEE Signal Process. Mag. 13, 47–60 (1996).
[CrossRef]

Moreno, J.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Moser, G.

S. B. Serpico and G. Moser, “Extraction of spectral channels from hyperspectral images for classification purposes,” IEEE Trans. Geosci. Remote Sens. 45, 484–495 (2007).
[CrossRef]

Petersen, K. B.

S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).

Rabiner, L.

L. Rabiner and B. Juang, Fundamentals of Speech Recognition (Prentice-Hall, 1993).

Ren, H.

Q. Du and H. Ren, “Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery,” Pattern Recogn. 36, 1–12 (2003).
[CrossRef]

Rubin, D. B.

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).

Serpico, S. B.

S. B. Serpico and G. Moser, “Extraction of spectral channels from hyperspectral images for classification purposes,” IEEE Trans. Geosci. Remote Sens. 45, 484–495 (2007).
[CrossRef]

S. B. Serpico and L. Bruzzone, “A new search algorithm for feature selection in hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 39, 1360–1367 (2001).
[CrossRef]

Shaw, G. A.

G. A. Shaw and H. Burke, “Spectral imaging for remote sensing,” Lincoln Lab. J. 14, 3–28 (2003).

Sheffield, M.

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Sigurdsson, S.

S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).

Soria-Olivas, E.

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

Sotudeh, R.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

Stock, D. G.

R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).

Subramanian, S.

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Tho, C. T.

P. F. Chen and C. T. Tho, “Hyperspectral imagery classification using a backpropagation neural network,” in 1994 IEEE International Conference on Neural Networks (IEEE, 1994), pp. 2942–2947.
[CrossRef]

Toomarian, N.

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Webb, A. R.

A. R. Webb, Statistical Pattern Recognition (Wiley, 2002).
[CrossRef]

Xu, J.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

IEEE Signal Process. Mag.

T. K. Moon, “The expectation-maximization algorithm,” IEEE Signal Process. Mag. 13, 47–60 (1996).
[CrossRef]

IEEE Trans. Acoust. Speech Signal Process.

S. B. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,” IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980).
[CrossRef]

IEEE Trans. Geosci. Remote Sens.

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

G. Camps-Valls, L. Gómez-Chova, J. Calpe-Maravilla, J. D. Martín-Guerrero, E. Soria-Olivas, L. Alonso-Chordá, and J. Moreno, “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42, 1530–1542 (2004).
[CrossRef]

S. B. Serpico and L. Bruzzone, “A new search algorithm for feature selection in hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 39, 1360–1367 (2001).
[CrossRef]

S. B. Serpico and G. Moser, “Extraction of spectral channels from hyperspectral images for classification purposes,” IEEE Trans. Geosci. Remote Sens. 45, 484–495 (2007).
[CrossRef]

S. Kumar, J. Ghosh, and M. M. Crawford, “Best-bases feature extraction algorithms for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 39, 1368–1379 (2001).
[CrossRef]

L. M. Bruce, C. H. Koger, and J. Li, “Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction,” IEEE Trans. Geosci. Remote Sens. 40, 2331–2338 (2002).
[CrossRef]

B. C. Kuo and D. A. Landgrebe, “Nonparametric weighted feature extraction for classification,” IEEE Trans. Geosci. Remote Sens. 42, 1096–1105 (2004).
[CrossRef]

IEEE Trans. Inf. Theory

G. F. Hughes, “On the mean accuracy of statistical pattern recognizers,” IEEE Trans. Inf. Theory 14, 55–63 (1968).
[CrossRef]

J. R. Stat. Soc. Ser. B. Methodol.

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. R. Stat. Soc. Ser. B. Methodol. 39, 1–38 (1977).

Lincoln Lab. J.

G. A. Shaw and H. Burke, “Spectral imaging for remote sensing,” Lincoln Lab. J. 14, 3–28 (2003).

Pattern Recogn.

Q. Du and H. Ren, “Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery,” Pattern Recogn. 36, 1–12 (2003).
[CrossRef]

Proc. SPIE

S. Subramanian, N. Gat, M. Sheffield, J. Barhen, and N. Toomarian, “Methodology for hyperspectral image classification using novel neural network,” Proc. SPIE 3071, 128–137(1997).
[CrossRef]

Other

P. F. Chen and C. T. Tho, “Hyperspectral imagery classification using a backpropagation neural network,” in 1994 IEEE International Conference on Neural Networks (IEEE, 1994), pp. 2942–2947.
[CrossRef]

A. R. Webb, Statistical Pattern Recognition (Wiley, 2002).
[CrossRef]

B. Javidi, Image Recognition and Classification Algorithms, Systems, and Applications (Marcel Dekker, 2002).
[CrossRef]

R. O. Duda, P. E. Hart, and D. G. Stock, Pattern Classification, 2nd ed. (Wiley, 2001).

L. Rabiner and B. Juang, Fundamentals of Speech Recognition (Prentice-Hall, 1993).

S. Sigurdsson, K. B. Petersen, and T. Lehn-Schiøler, “Mel frequency cepstral coefficients: an evaluation of robustness of MP3 encoded music,” in Proceedings of the 7th International Symposium on Music Information Retrieval (2006).

T. Ganchev, N. Fakotakis, and G. Kokkinakis, “Comparative evaluation of various MFCC implementations on the speaker verification task,” in Proceedings of the 10th International Conference on Speech and Computer (2005), pp. 191–194.

J. Xu, A. Ariyaeeinia, R. Sotudeh, and Z. Ahmad, “Pre-processing speech signals in FPGAs,” in Proceedings of the 6th International Conference on ASIC 2005 (IEEE, 2005), pp. 778–782.

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 (3)

Fig. 1
Fig. 1

Speech signal and spectral reflectance signal: (a) a speech signal, (b) fraction of the speech signal, (c) selected fraction, (d) hyperspectral scene, (e) local of the hyperspectral scene, and (f) selected spectral reflectance signal.

Fig. 2
Fig. 2

Classification results of the first test: (a) hyperspectral scene (band 34), (b) standard classification, (c) classification result using PCA feature, (d) classification result using LDA feature, and (e) classification result using MFCC feature.

Fig. 3
Fig. 3

Classification results of the second test: (a) hyperspectral scene (band 21), (b) standard classification, (c) classification result using PCA feature, (d) classification result using LDA feature, and (e) classification result using MFCC feature.

Tables (2)

Tables Icon

Table 1 Confusion Matrix of the First Test

Tables Icon

Table 2 Confusion Matrix of the Second Test

Equations (20)

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

x e ( n ) = x ( n ) μ x ( n 1 ) ,
w ( n ) = 0.54 0.46 cos ( 2 n π N 1 ) ,
y ( n ) = w ( n ) x e ( n ) ,
S ( n ) = DFT [ y ( n ) ] = R ( n ) + j I ( n ) ,
P ( n ) = | S ( n ) | = R 2 ( n ) + I 2 ( n ) ,
F P ( m ) = n = 0 N / 2 1 H m ( n ) P ( n ) ,
ξ = 2595 log 10 ( f 700 + 1 ) ,
f c ( m ) = 700 ( 10 ξ c ( m ) / 2595 1 ) ,
H m ( n ) = { 0 for     f ( n ) < f c ( m 1 ) f ( n ) f c ( m 1 ) f c ( m ) f c ( m 1 ) for     f c ( m 1 ) f ( n ) < f c ( m ) f ( n ) f c ( m + 1 ) f c ( m ) f c ( m + 1 ) for     f c ( m ) f ( n ) < f c ( m + 1 ) 0 for     f c ( m + 1 ) f ( n ) ,
L P ( m ) = ln [ F P ( m ) ] .
C P ( k ) = m = 0 M 1 L P ( m ) cos [ ( m + 0.5 ) k π M ] ,
Φ ( n ) = arctan [ I ( n ) R ( n ) ] .
Φ N ( n ) = Φ ( n ) + π 2 .
F Φ ( m ) = n = 0 N / 2 1 H m ( n ) Φ N ( n ) .
L Φ ( m ) = ln [ F Φ ( m ) ] ,
C Φ ( k ) = m = 0 M 1 L Φ ( m ) cos [ ( m + 0.5 ) k π M ] .
v = [ v 1 , v 2 , , v M ] ,
v k = C P , s ( k ) + C Φ , s ( k ) ,
C P , s ( k ) = C P ( k ) C P 2 ( 1 ) + C P 2 ( 2 ) + + C P 2 ( M ) ,
C Φ , s ( k ) = C Φ ( k ) C Φ 2 ( 1 ) + C Φ 2 ( 2 ) + + C Φ 2 ( M ) .

Metrics