Abstract

In this paper, we present a novel approach for face verification using local binary pattern (LBP) operators and optical correlation filters. Due to selected filter type and LBP method, different performances would have been expected. We let LBP operate on training images to form local binary pattern–unconstrained minimum average correlation energy (LBP-UMACE) filters as an optical correlation filter to enhance recognition rates and reduce error rates simultaneously. As a result, we demonstrate that the designed filters have better performance compared with UMACE filters. Moreover, the proposed filters are easy to implement and can be used in fast and reliable face verification systems.

© 2012 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. S. A. Samad, D. A. Ramli, and A. Hussain, “Region selection for robust face verification using UMACE filters,” in Proceedings of the International Conference on Electrical Engineering and Informatics (Mercu Buana University Research, 2007), p. 67. http://research.mercubuana.ac.id
  2. K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).
  3. B. V. K. V. Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
    [CrossRef]
  4. B. V. K. V. Kumar, A. Mahalanobis, and R. D. Juday, Correlation Pattern Recognition (Cambridge University, 2005).
  5. A. Mahalanobis, B. V. K. V. Kumar, and D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3640 (1987).
    [CrossRef]
  6. K. Venkataramani and B. V. K. Vijayakumar, “Fingerprint verification using correlation filters,” in Lecture Notes in Computer Science, Vol. 2688 (Springer, 2003), pp. 886–894.
  7. T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
    [CrossRef]
  8. T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, 2004), pp. 469–481.
  9. A. Hadid, M. Pietikäinen, and T. Ahonen, “A discriminative feature space for detecting and recognizing faces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2004).
  10. T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
    [CrossRef]
  11. http://cvc.yale.edu : Yale B Face Database.
  12. K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).

2002 (1)

T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
[CrossRef]

1996 (1)

T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
[CrossRef]

1992 (1)

1987 (1)

Ahonen, T.

T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, 2004), pp. 469–481.

A. Hadid, M. Pietikäinen, and T. Ahonen, “A discriminative feature space for detecting and recognizing faces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2004).

Casasent, D.

Hadid, A.

A. Hadid, M. Pietikäinen, and T. Ahonen, “A discriminative feature space for detecting and recognizing faces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2004).

T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, 2004), pp. 469–481.

Harwood, D.

T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
[CrossRef]

Hussain, A.

S. A. Samad, D. A. Ramli, and A. Hussain, “Region selection for robust face verification using UMACE filters,” in Proceedings of the International Conference on Electrical Engineering and Informatics (Mercu Buana University Research, 2007), p. 67. http://research.mercubuana.ac.id

Juday, R. D.

B. V. K. V. Kumar, A. Mahalanobis, and R. D. Juday, Correlation Pattern Recognition (Cambridge University, 2005).

Kumar, B. V. K. V.

Mäenpää, T.

T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
[CrossRef]

Mahalanobis, A.

A. Mahalanobis, B. V. K. V. Kumar, and D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3640 (1987).
[CrossRef]

B. V. K. V. Kumar, A. Mahalanobis, and R. D. Juday, Correlation Pattern Recognition (Cambridge University, 2005).

Ojala, T.

T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
[CrossRef]

T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
[CrossRef]

Pietikäinen, M.

T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
[CrossRef]

T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
[CrossRef]

T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, 2004), pp. 469–481.

A. Hadid, M. Pietikäinen, and T. Ahonen, “A discriminative feature space for detecting and recognizing faces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2004).

Ramli, D. A.

S. A. Samad, D. A. Ramli, and A. Hussain, “Region selection for robust face verification using UMACE filters,” in Proceedings of the International Conference on Electrical Engineering and Informatics (Mercu Buana University Research, 2007), p. 67. http://research.mercubuana.ac.id

Samad, S. A.

S. A. Samad, D. A. Ramli, and A. Hussain, “Region selection for robust face verification using UMACE filters,” in Proceedings of the International Conference on Electrical Engineering and Informatics (Mercu Buana University Research, 2007), p. 67. http://research.mercubuana.ac.id

Venkataramani, K.

K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).

K. Venkataramani and B. V. K. Vijayakumar, “Fingerprint verification using correlation filters,” in Lecture Notes in Computer Science, Vol. 2688 (Springer, 2003), pp. 886–894.

K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).

Vijayakumar, B. V. K.

K. Venkataramani and B. V. K. Vijayakumar, “Fingerprint verification using correlation filters,” in Lecture Notes in Computer Science, Vol. 2688 (Springer, 2003), pp. 886–894.

Appl. Opt. (2)

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

T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002).
[CrossRef]

Pattern Recogn. (1)

T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distribution,” Pattern Recogn. 29, 51–59 (1996).
[CrossRef]

Other (8)

T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, 2004), pp. 469–481.

A. Hadid, M. Pietikäinen, and T. Ahonen, “A discriminative feature space for detecting and recognizing faces,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2004).

http://cvc.yale.edu : Yale B Face Database.

K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).

S. A. Samad, D. A. Ramli, and A. Hussain, “Region selection for robust face verification using UMACE filters,” in Proceedings of the International Conference on Electrical Engineering and Informatics (Mercu Buana University Research, 2007), p. 67. http://research.mercubuana.ac.id

K. Venkataramani, “Reduced correlation filters for fingerprint verification,” M. Sc. dissertation (Carnegie Mellon University, 2002).

B. V. K. V. Kumar, A. Mahalanobis, and R. D. Juday, Correlation Pattern Recognition (Cambridge University, 2005).

K. Venkataramani and B. V. K. Vijayakumar, “Fingerprint verification using correlation filters,” in Lecture Notes in Computer Science, Vol. 2688 (Springer, 2003), pp. 886–894.

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.

Schematic of the correlation filter approach to verification.

Fig. 2.
Fig. 2.

Illustration of peak-to-sidelobe-ratio (PSR) computation.

Fig. 3.
Fig. 3.

The basic LBP operator [8].

Fig. 4.
Fig. 4.

Two examples of the extended LBP [10]: the circular (8, 1) neighborhood and the circular (16, 2) neighborhood, respectively.

Fig. 5.
Fig. 5.

Training and test stage for LBP-UMACE filters.

Fig. 6.
Fig. 6.

Examples of images of one person from the Extended Yale B frontal database. The columns respectively give images from subsets 1 to 5.

Fig. 7.
Fig. 7.

Recognition rate comparison between LBB-UMACE and UMACE with PSR = 10 and LBP 8 , 1 .

Fig. 8.
Fig. 8.

Average error rates comparison between LBB-UMACE and UMACE with PSR = 10 and LBP 8 , 1 .

Fig. 9.
Fig. 9.

LBP-UMACE filter ROC curve for person No. 1.

Tables (3)

Tables Icon

Table 1. Recognition Results of UMACE Filters for First Five Persons with PSR Threshold = 10a

Tables Icon

Table 2. Recognition Results of LBP-UMACE Filters for Five Persons with PSR Threshold = 10 and LBP 8 , 1 a

Tables Icon

Table 3. Selected PSR Values for 10 First LBP-UMACE Filters

Equations (10)

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

PSR = peak mean standard deviation .
g ( x , y ) = f ( x , y ) × h ( x , y ) ,
E i = x = 0 d 1 y = 0 d 1 | g i ( x , y ) | 2 .
E i = 1 d 2 u = 0 d 1 v = 0 d 1 | G i ( u , v ) | 2 ,
E i = 1 d 2 u = 0 d 1 v = 0 d 1 | H i ( u , v ) | 2 | X i ( u , v ) | 2 = h + D i h ,
ACH = 1 N k = 1 N E k = 1 N k = 1 N h + D k h = h + D h .
g i ( x , y ) = u = 0 d 1 v = 0 d 1 F i ( u , v ) · H ( u , v ) * e j 2 π u x d e j 2 π v y d
g i ( 0 , 0 ) = u = 0 d 1 v = 0 d 1 F i ( u , v ) · H ( u , v ) * = h + X i
J ( h ) = h + m m + h h + D h
h = D 1 m

Metrics