Skip to main content
Log in

Generalized Gabor filters for palmprint recognition

  • Industrial and Commercial Application
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Orientation-based coding approaches have recently been widely employed for face and palmprint recognition where generally, one starts with a set of Gabor filters to extract orientation information and then proceeds to code dominant orientations as features for each point of the palmprint. However, as the Gabor filter is developed to model two-dimensional receptive fields of simple cells in straits cortex, it might not be our best choice when dealing with curved and complex structures inherent in the palmprint texture. Motivated by this intuition, this paper shows that Gabor filters are a subset of a bigger family of filters which we refer to as generalized Gabor filter (GGF). Depending on the values of its parameters, a GGF takes a rather diverse shapes and orientations, which results in a potentially finer feature extraction capability. We show this improved capability by employing GGFs in the palmprint verification process. In applying our method, two different sub-banks of GGFs are defined for the orientation-based feature extraction of palmprints, and when compared with Gabor filters, it will be shown that GGFs have the upper hand in capturing orientation features. Furthermore, compared with the competitive code—one of the well-known orientation-based coding methods—the number of employed orientations is reduced to half. This would automatically compensate for a double usage of the filter banks, which otherwise could increase the time complexity of using GGFs. These ideas are further elaborated using a set of experiments on PolyU II and PolyU 2D/3D palmprint databases. The results show the preeminence of using GGFs both in terms of accuracy and efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Zhang D, Zuo W, Yue F (2012) A comparative study of palmprint recognition algorithms. ACM Comput Surv 44(1):2

    Article  Google Scholar 

  2. Lu G, Zhang D, Wang K (2003) Palmprint recognition using Eigenpalm features. Pattern Recognit Lett 24(9):1463–1467

    Article  MATH  Google Scholar 

  3. Xu Y, Zhang D, Yang JY (2010) A feature extraction method for use with bimodal biometrics. Pattern Recognit 43(3):1106–1115

    Article  MATH  Google Scholar 

  4. Xu Y, Yang JY, Jin Z (2004) A novel method for fisher discriminant analysis. Pattern Recognit 37(2):381–384

    Article  MATH  Google Scholar 

  5. Zhang Y, Sun D, Qiu Z (2012) Hand-based single sample biometrics recognition. Neural Comput Appl 21(8):1835–1844

    Article  Google Scholar 

  6. Kokiopoulou E, Saad Y (2007) Orthogonal neighborhood preserving projections: a projection-based dimensionality reduction technique. IEEE Trans Pattern Anal Mach Intell 29(12):2143–2156

    Article  Google Scholar 

  7. He X, Cai D, Yan S, Zhang HJ (2005) Neighborhood preserving embedding. In: International conference on computer visio (ICCV), pp 1208–1213

  8. Wang Y, Wu Y (2010) Complete neighborhood preserving embedding for face recognition. Pattern Recognit 43(3):1008–1015

    Article  MATH  Google Scholar 

  9. Sang H, Yuan W, Zhang Z (2009) Research of palmprint recognition based on 2DPCA. In: International symp on neural networks (ISNN), pp 831–838

  10. Li M, Yuan B (2005) 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recognit Lett 26(5):527–532

    Article  Google Scholar 

  11. Hu D, Feng G, Zhou Z (2007) Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition. Pattern Recognit 40(1):339–342

    Article  MATH  Google Scholar 

  12. Zhang H, Wu QJ, Chow TW, Zhao M (2012) A two-dimensional Neighborhood Preserving Projection for appearance-based face recognition. Pattern Recognit 45(5):1866–1876

    Article  MATH  Google Scholar 

  13. Du H, Wang S, Zhao J, Xu N (2010) Two-dimensional neighborhood preserving embedding for face recognition. In: Information management and engineering (ICIME), pp 500–504

  14. Wang Y, Xie JB, Wu Y (2014) Two-dimensional complete neighborhood preserving embedding. Neural Comput and Appl 24(7–8):1505–1517

    Article  Google Scholar 

  15. Nibouche O, Jiang J, Trundle P (2012) Analysis of performance of palmprint matching with enforced sparsity. Digital Signal Process 22(2):348–355

    Article  MathSciNet  Google Scholar 

  16. Guo XM, Wan LM, Wang CY (2014) A palmprint recognition based on collaborative representation. In: Applied mechanics and materials, pp 1317–1322

  17. Wei L, Xu F, Yin J, Wu A (2014) Kernel locality-constrained collaborative representation based discriminant analysis. Knowl Syst 40:212–220

    Article  Google Scholar 

  18. Kong A, Zhang D (2004) Competitive coding scheme for palmprint verification. In: International conference on pattern recognit, pp 520–523

  19. Duta N, Jain A, Mardia K (2002) Matching of palmprints. Pattern Recognit Lett 23(4):477–485

    Article  MATH  Google Scholar 

  20. Han C, Cheng H, Lin C, Fan K (2003) Personal authentication using palm-print features. Pattern Recognit 36(2):371–381

    Article  Google Scholar 

  21. Lin S, Yuan WQ, Wu W, Fang T (2012) Blurred palmprint recognition based on DCT and block energy of principal line. J Optoelectron Laser 23(11):2200–2206

    Google Scholar 

  22. Dai J, Feng J, Zhou J (2012) Robust and efficient ridge-based palmprint matching. IEEE Trans Pattern Anal Mach Intell 34(8):1618–1632

    Article  Google Scholar 

  23. Liu E, Jain AK, Tian J (2013) A coarse to fine minutiae-based latent palmprint matching. IEEE Trans Pattern Anal Mach Intell 35:2307–2322

    Article  Google Scholar 

  24. Chen F, Huang X, Zhou J (2013) Hierarchical minutiae matching for fingerprint and palmprint identification. IEEE Trans Image Process 22(12):4964–4971

    Article  MathSciNet  MATH  Google Scholar 

  25. Zhang D, Kong WK, You J, Wong M (2003) Online palmprint identification. IEEE Trans Pattern Anal Mach Intell 25(9):1041–1050

    Article  Google Scholar 

  26. Kong A, Zhang D, Kamel M (2006) Palmprint identification using feature-level fusion. Pattern Recognit 39(3):478–487

    Article  MATH  Google Scholar 

  27. Jia W, Huang DS, Zhang D (2008) Palmprint verification based on robust line orientation code. Pattern Recognit 41(5):1504–1513

    Article  MATH  Google Scholar 

  28. Yue F, Zuo W, Zhang D, Wang K (2009) Orientation selection using modified FCM for competitive code-based palmprint recognition. Pattern recognit 42(11):2841–2849

    Article  MATH  Google Scholar 

  29. TamrakarD Khanna P (2015) Palmprint verification with XOR-SUM Code. Signal image and video process 9(3):535–542

    Article  Google Scholar 

  30. Sun Z, Tan T, Wang Y, Li SZ (2005) Ordinal palmprint representation for personal identification. In: Computer vision and pattern recognitio (CVPR), pp 279–284

  31. Wu X, Wang K, Zhang D (2006) Palmprint texture analysis using derivative of Gaussian filters. In: Computational intelligence and security, pp 751–754

  32. Fei L, Xu Y, Tang W, Zhang D (2016) Double-orientation code and nonlinear matching scheme for palmprint recognition. Pattern Recognit 49:89–101

    Article  Google Scholar 

  33. Fei L, Xu Y, Zhang D (2016) Half-orientation extraction of palmprint features. Pattern Recognit Lett 69:35–41

    Article  Google Scholar 

  34. Guo Z, Zhang D, Zhang L, Zuo W (2009) Palmprint verification using binary orientation co-occurrence vector. Pattern Recognit Lett 30(13):1219–1227

    Article  Google Scholar 

  35. Zhang L, Li H, Niu J (2012) Fragile bits in palmprint recognition. IEEE Signal Process Lett 19(10):663–666

    Article  Google Scholar 

  36. Zuo W, Lin Z, Guo Z, Zhang D (2010) The multiscale competitive code via sparse representation for palmprint verification. In: Computer vision and pattern recognition (CVPR), pp 2265–2272

  37. Tamrakar D, Khanna P (2011) Palmprint verification using competitive index with PCA. In: Signal Processing, Communication, Computing and Networking Technologies (ICSCCN), pp 768–771

  38. Luo YT, Zhao LY, Zhang B, Jia W, Xue F, Lu JT, Zhu YH, Xu BQ (2016) Local line directional pattern for palmprint recognition. Pattern Recognit 50:26–44

    Article  Google Scholar 

  39. Yue F, Zuo W, Wang K, Zhang D (2008) A performance evaluation of filter design and coding schemes for palmprint recognition. In: International conference on pattern recognition (ICPR), pp 1–4

  40. Pan X, Ruan QQ (2008) Palmprint recognition using Gabor feature-based (2D)2PCA. Neurocomputing 71(13):3032–3036

    Article  Google Scholar 

  41. Cui L, Wei Y, Tang YY, Li H (2010) Gabor-based tensor local discriminant embedding and its application on palmprint recognition. Int J Wavel Multiresolution Inf Process 8(2):327–342

    Article  MathSciNet  MATH  Google Scholar 

  42. Gabor D (1946) Theory of communication. J Institut Electric Eng 93:429–457

    Google Scholar 

  43. Daugman J (1980) Two-dimensional spectral analysis of cortical receptive field profiles. Vis Res 20(10):847–856

    Article  Google Scholar 

  44. Lee TS (1996) Image Representation Using 2D Gabor Wavelets. IEEE Trans Pattern Anal Mach Intell 18(10):1–13

    Google Scholar 

  45. Fei L, Zhang B, Xu Y, Yan L (2016) Palmprint recognition using neighboring direction indicator. IEEE Trans Human Mach Syst 46(6):787–798

    Article  Google Scholar 

  46. Gradshteyn IS, Ryzhik IM (2007) Table of Integrals, Series, and Products. 7th edition, pp 365

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Abdolmajid Mousavi.

Appendix

Appendix

We divide Eq. (4) into two parts based on distributive law:

$$\begin{aligned} B\left( {x,y,x_{0} ,y_{0} ,\eta ,\theta ,\omega_{0} } \right) & = B_{1} + B_{2} = \frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{\eta } \\ & \quad \times \exp \left( { - \frac{{\omega_{0}^{2} }}{{8\kappa^{2} }}\left( {4\left( {\left( {x - x_{0} } \right)\cos \theta + \left( {y - y_{0} } \right)\sin \theta } \right)^{2} + \xi \left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{2} } \right)} \right) \\ & \quad \times \exp \left( {i\left( {\omega_{0} \left( {x - x_{0} } \right)\cos \theta + \omega_{0} \left( {y - y_{0} } \right)\sin \theta } \right)} \right) - \frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{\eta } \\ & \quad \times \exp \left( { - \frac{{\omega_{0}^{2} }}{{8\kappa^{2} }}\left( {4\left( {\left( {x - x_{0} } \right)\cos \theta + \left( {y - y_{0} } \right)\sin \theta } \right)^{2} + \xi \left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{2} } \right)} \right) \times \exp \left( { - \frac{{\kappa^{2} }}{2}} \right). \\ \end{aligned}$$
(13)

For the first term, the 2-D Fourier transform of the GG wavelet defined in Eq. (4) is given by

$$\begin{aligned} \bar{B}_{1} \left( {u,v } \right) & = \int \int \frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{\eta } \\ & \quad \times \exp \left( { - \frac{{\omega_{0}^{2} }}{{8\kappa^{2} }}\left( {4\left( {\left( {x - x_{0} } \right)\cos \theta + \left( {y - y_{0} } \right)\sin \theta } \right)^{2} + \xi \left( { - \left( {x - x_{0} } \right)\sin \theta + \left( {y - y_{0} } \right)\cos \theta } \right)^{2} } \right)} \right) \\ & \quad \times \left[ {\exp \left( {i\left( {u_{0} \left( {x - x_{0} } \right) + v_{0} \left( {y - y_{0} } \right)} \right)} \right)} \right]\exp \left( { - i\left[ {ux + vy} \right]} \right)dxdy \\ \end{aligned}$$
(14)

where \(u_{0} = \omega_{0} \cos \theta\) and \(v_{0} = \omega_{0} \sin \theta\). We rewrite the wavelet formula to include a coefficient, a Gaussian envelope, and a sinusoid carrier in \(N\)-dimensions.

$$\bar{B}_{1} \left( {u,v } \right) = K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]S\left( {X - X_{0} } \right).$$
(15)

\(K\left( {X - X_{0} } \right)^{\eta }\) (the coefficient), \(\wp \left( z \right)\)(the Gaussian envelope), and \(S\left( z \right)\)(the sinusoidal carrier) are defined as follows:

$$\wp \left( Z \right) = \exp \left( { - Z^{T} Z} \right)$$
(16)
$$S\left( Z \right) = \exp \left( { - jU_{0}^{T} Z} \right).$$
(17)

The Fourier transform of this function could be derived as:

$$\begin{aligned} \bar{B}\left( U \right) & = \mathop \int \nolimits_{ - \infty }^{ + \infty } K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]\exp \left( {jU_{0}^{T} \left( {X - X_{0} } \right)} \right)\exp \left( { - jU^{T} X} \right)dX \\ & \quad = \exp \left( { - jU_{0}^{T} X_{0} } \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]\exp \left( {jU_{0}^{T} X} \right)\exp \left( { - jU^{T} X} \right)dX \\ & \quad = \exp \left( { - jU_{0}^{T} X_{0} } \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]\exp \left( { - j\left( {U - U_{0} } \right)^{T} X} \right)dX \\ \end{aligned}$$
(18)

let \(\bar{X} = A\left( {X - X_{0} } \right).\) Then, we have \(d\bar{X} = AdX\). So:

$$\bar{B}_{1} \left( U \right) = \frac{K}{{A^{\eta + 1} }}\exp \left( { - jU_{0}^{T} X_{0} } \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } \bar{X}^{\eta } \wp \left[ {\bar{X}} \right]\exp \left[ { - j\left( {U - U_{0} } \right)^{T} \left( {A^{ - 1} \bar{X} + X_{0} } \right)} \right]d\bar{X}$$
(19)
$$\Rightarrow \bar{B}_{1} \left( U \right) = \frac{K}{{A^{\eta + 1} }}\exp \left[ { - j\left( {U - U_{0} } \right)^{T} X_{0} } \right]\exp \left( { - jU_{0}^{T} X_{0} } \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } \bar{X}^{\eta } \wp \left[ {\bar{X}} \right]\exp \left[ { - j\left(A^{ - T} \left( {U - U_{0} } \right) \right)^{T} \bar{X}} \right]d\bar{X}.$$
(20)

Since(see [46]): \(\mathop \int \nolimits_{ - \infty }^{ + \infty } x^{\eta } \exp \left( { - px^{2} + 2qx} \right)dx = \frac{1}{{2^{\eta - 1} p}}\sqrt {\frac{\pi }{p}} \frac{{d^{\eta - 1} }}{{dq^{\eta - 1} }}\left( {q\exp \left( {\frac{{q^{2} }}{p}} \right)} \right),\quad p > 0.\) We have \(\bar{B}_{1} \left( U \right) = \frac{K}{{A^{\eta + 1} }}\exp \left[ { - j\left( {U - U_{0} } \right)^{T} X_{0} } \right]\exp \left( { - jU_{0}^{T} X_{0} } \right)\frac{1}{{2^{\eta - 1} }}\sqrt \pi \frac{{d^{\eta - 1} }}{{d\left( { - j\left(A^{ - T} \left( {U - U_{0} } \right)\right)^{T}/2} \right)^{\eta - 1} }}\left( {\left( { - j\left ( A^{ - T} \left( {U - U_{0} } \right) \right)^{T}/2} \right) \exp \left( {{\raise0.7ex\hbox{${\left(A^{ - 2T} \left( {U - U_{0} } \right)^{2}\right)^{T} }$} \!\mathord{\left/ {\vphantom {{A^{-T} \left( {U - U_{0} } \right)^{2} } 4}}\right.\kern-0pt} \!\lower0.7ex\hbox{$4$}}} \right)} \right).\)

Here, \(K = \frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left[ {0 1} \right]^{\eta } \left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]^{\eta }\), \(A = C \cdot R\) where \(C = \left[ {\begin{array}{*{20}c} {i\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} } & 0 \\ 0 & {i\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} } \\ \end{array} } \right]\) is the coefficient matrix and \(R = \left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]\) is the rotation matrix. Since \(R\) is a rotation:

$$A^{ - 1} = C^{ - 1} R^{ - T}$$
(21)
$$A^{ - T} = RC^{ - 1} = C^{ - 1} R$$
(22)
$$||A|| = ||C|| \cdot ||R|| = \frac{{\omega_{0}^{2} \sqrt \xi }}{{4\kappa^{2} }}$$
(23)
$$\begin{aligned} \Rightarrow A^{ - T} & = \left[ {\begin{array}{*{20}c} {i\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} } & 0 \\ 0 & {i\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} } \\ \end{array} } \right]^{ - 1} \left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right] = - \frac{1}{{\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} }}\left[ {\begin{array}{*{20}c} {i\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} } & 0 \\ 0 & {i\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} } \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right] = \\ & \quad - \frac{1}{{\frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}}}\left[ {\begin{array}{*{20}c} {i\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \cos \theta } & {i\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \sin \theta } \\ {i\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \sin \theta } & {i\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \cos \theta } \\ \end{array} } \right]. \\ \end{aligned}$$
(24)

Let \(\varUpsilon \left( { A^{-T} \left( {U - U_{0} }\right) } \right) = \frac{{d^{\eta - 1} }}{{d\left( { - j\left(A^{ - T} \left( {U - U_{0} } \right)\right)^{T}/2} \right)^{\eta - 1} }}\left( {\left( { - j\left(A^{ - T} \left( {U - U_{0} } \right)\right)^{T}/2} \right)\exp \left( {{\raise0.7ex\hbox{${\left(A^{ - 2T} \left( {U - U_{0} } \right)^{2}\right)^{T} }$} \!\mathord{\left/ {\vphantom {{A^{ - 2T} \left( {U - U_{0} } \right)^{2} } 4}}\right.\kern-0pt} \!\lower0.7ex\hbox{$4$}}} \right)} \right).\) Since the GGF is a two-dimensional wavelet, we have

$$\bar{B}_{1} \left( {u,v} \right) = \frac{K}{{A^{\eta + 1} }}\frac{1}{{2^{\eta - 1} }}\sqrt \pi \exp \left[ { - j\left( {ux_{0} + vy_{0} } \right)} \right]\varUpsilon \left( {\left[ {\begin{array}{*{20}c} {u - u_{0} } \\ {v - v_{0} } \\ \end{array} } \right]} \right)$$
(25)
$$\begin{aligned} \bar{B}_{1} \left( {u,v} \right) & = \frac{{\frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left[ {\begin{array}{*{20}c} 0 & 1 \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]^{\eta } }}{{\left( { - \frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}} \right)^{\eta + 1} }}\exp \left[ { - j\left( {ux_{0} + vy_{0} } \right)} \right] \\ & \quad \varUpsilon \left( { - \frac{i}{{\frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}}}\left[ {\begin{array}{*{20}c} {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \cos \theta } & {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \sin \theta } \\ { - \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \sin \theta } & {\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \cos \theta } \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {u - u_{0} } \\ {v - v_{0} } \\ \end{array} } \right]} \right) \\ & \quad = \frac{{\frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left[ {\begin{array}{*{20}c} 0 & 1 \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]^{\eta } }}{{\left( { - \frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}} \right)^{\eta + 1} }}\exp \left[ { - j\left( {ux_{0} + vy_{0} } \right)} \right]\varUpsilon \left( { - \frac{i}{{\frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}}}\left[ {\begin{array}{*{20}c} {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \left( {u - u_{0} } \right)\cos \theta + \sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \left( {v - v_{0} } \right)\sin \theta } \\ { - \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \left( {u - u_{0} } \right)\sin \theta + \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \left( {v - v_{0} } \right)\cos \theta } \\ \end{array} } \right]} \right) \\ \end{aligned}$$
(26)

For the second term we have:

$$\begin{aligned} \bar{B}_{2} \left( U \right) & = \mathop \int \nolimits_{ - \infty }^{ + \infty } K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]\exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\exp \left( { - jU^{T} X} \right)dX \\ & \quad = \exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } K\left( {X - X_{0} } \right)^{\eta } \wp \left[ {A\left( {X - X_{0} } \right)} \right]\exp \left( { - jU^{T} X} \right)dX \\ \end{aligned}$$
(27)

let \(\bar{X} = A\left( {X - X_{0} } \right).\) Then, we have \(d\bar{X} = AdX.\) So:

$$\bar{B}_{2} \left( U \right) = \frac{K}{{A^{\eta + 1} }}\exp\left( { - \frac{{\kappa^{2} }}{2}} \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } \bar{X}^{\eta } \wp \left[ {\bar{X}} \right]\exp \left[ { - jU^{T} \left( {A^{ - 1} \bar{X} + X_{0} } \right)} \right]d\bar{X}$$
(28)
$$\Rightarrow \bar{B}_{2} \left( U \right) = \frac{K}{{A^{\eta + 1} }}\exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\exp \left(-jU^{T}X_{0} \right)\mathop \int \nolimits_{ - \infty }^{ + \infty } \bar{X}^{\eta } \wp \left[ {\bar{X}} \right]\exp \left[ { - jA^{ - T} U\bar{X}} \right]d\bar{X}.$$
(29)

Since (see [46]) \(\mathop \int \nolimits_{ - \infty }^{ + \infty } x^{\eta } \exp \left( { - px^{2} + 2qx} \right)dx = \frac{1}{{2^{\eta - 1} p}}\sqrt {\frac{\pi }{p}} \frac{{d^{\eta - 1} }}{{dq^{\eta - 1} }}\left( {q\exp \left( {\frac{{q^{2} }}{p}} \right)} \right),\quad p > 0.\)We have \(\bar{B}\left( U \right) = \frac{K}{{A^{\eta + 1} }}exp\left( { - \frac{{\kappa^{2} }}{2}} \right)\exp \left(-jU^{T}X_{0}\right)\frac{1}{{2^{\eta - 1} }}\sqrt \pi \frac{{d^{\eta - 1} }}{{d\left( { - j\left(A^{ - T} U\right)^{T}/2} \right)^{\eta - 1} }}\left( {\left( { - j\left(A^{ - T} U\right)^{T}/2} \right)\exp \left( {{\raise0.7ex\hbox{${\left(A^{ - 2T} U^{2} \right)^{T}}$} \!\mathord{\left/ {\vphantom {{A^{ - 2T} U^{2} } 4}}\right.\kern-0pt} \!\lower0.7ex\hbox{$4$}}} \right)} \right).\) Let \(\phi \left( {U} \right) = \frac{{d^{\eta - 1} }}{{d\left( { - j\left(A^{ - T} U\right)^{T}/2} \right)^{\eta - 1} }}\left( {\left( { - j\left(A^{ - T} U\right)^{T}/2} \right)\exp \left( {{\raise0.7ex\hbox{${\left(A^{ - 2T} U^{2}\right)^{T} }$} \!\mathord{\left/ {\vphantom {{A^{ - 2T} U^{2} } 4}}\right.\kern-0pt} \!\lower0.7ex\hbox{$4$}}} \right)} \right).\) Since the GGF is a two-dimensional wavelet, we have

$$\bar{B}_{2} \left( {u,v} \right) = \frac{K}{{A^{\eta + 1} }}\exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\exp\left(-jU^{T}X_{0}\right)\frac{1}{{2^{\eta - 1} }}\sqrt \pi \phi \left( {A^{-T} \left[ {\begin{array}{*{20}c} u \\ v \\ \end{array} } \right]} \right)$$
(30)
$$\begin{aligned} \bar{B}_{2} \left( {u,v} \right) & = \frac{{\frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left[ {\begin{array}{*{20}c} 0 & 1 \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]^{\eta } }}{{\left( { - \frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}} \right)^{\eta + 1} }}\exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\exp\left(-j\left(ux_{0}+vy_{0}\right) \right)\frac{1}{{2^{\eta - 1} }}\phi \left( { - \frac{i}{{\frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}}}\left[ {\begin{array}{*{20}c} {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \cos \theta } & {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} \sin \theta } \\ { - \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \sin \theta } & {\sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} \cos \theta } \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} u \\ v \\ \end{array} } \right]} \right) \\ & \quad = \frac{{\frac{{\omega_{0} }}{{\sqrt {2\pi } \kappa }}\left[ {\begin{array}{*{20}c} 0 & 1 \\ \end{array} } \right]\left[ {\begin{array}{*{20}c} {\cos \theta } & {\sin \theta } \\ { - \sin \theta } & {\cos \theta } \\ \end{array} } \right]^{\eta } }}{{\left( { - \frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}} \right)^{\eta + 1} }}\exp \left( { - \frac{{\kappa^{2} }}{2}} \right)\left(-j\left(ux_{0}+vy_{0}\right)\right)\frac{1}{{2^{\eta - 1} }}\phi \left( { - \frac{i}{{\frac{{\sqrt \xi \omega_{0}^{2} }}{{4\kappa^{2} }}}}\left[ {\begin{array}{*{20}c} {\sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} u\cos \theta + \sqrt {\frac{{\omega_{0}^{2} \xi }}{{8\kappa^{2} }}} v \sin \theta } \\ { - \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} u\sin \theta + \sqrt {\frac{{\omega_{0}^{2} }}{{2\kappa^{2} }}} v \cos \theta } \\ \end{array} } \right]} \right). \\ \end{aligned}$$
(31)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tabejamaat, M., Mousavi, A. Generalized Gabor filters for palmprint recognition. Pattern Anal Applic 21, 261–275 (2018). https://doi.org/10.1007/s10044-017-0638-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-017-0638-3

Keywords

Navigation