Advertisement

On New Radon-Based Translation, Rotation, and Scaling Invariant Transform for Face Recognition

  • Tomasz Arodź
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3039)

Abstract

The Radon transform has some interesting properties concerning the scaling, rotation-in-plane and translation of the input image. In the paper, these properties are a basis for deriving a transformation invariant to the aforementioned spatial image variations, a transformation that uses direct translation, angle representation and 1-D Fourier transform. As the face images often differ in pose and scale of the face, such a transformation can ease the recognition task. Experimental results show that the proposed method can achieve 96% and 89% recognition accuracy for, respectively, uniformly and non-uniformly illuminated images.

Keywords

Face recognition Radon transform Invariant recognition 

References

  1. 1.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)CrossRefGoogle Scholar
  2. 2.
    Brandt, R.D., Lin, F.: Representations that uniquely characterize images modulo translation, rotation and scaling. Pattern Recognition Letters 17, 1001–1015 (1996)CrossRefGoogle Scholar
  3. 3.
    Hu, M.K.: Visual pattern recognition by moment invariants. IEEE Trans. Inform. Theory IT-8, 179–187 (1962)Google Scholar
  4. 4.
    Khalil, M.I., Bayoumi, M.M.: Affine invariants for object recognition using the wavelet transform. Pattern Recognition Letters 23, 57–72 (2002)zbMATHCrossRefGoogle Scholar
  5. 5.
    Kim, H.-K., Kim, J.-D.: Region-based shape descriptor invariant to rotation, scale and translation. Signal Processing: Image Communication 16, 87–93 (2000)CrossRefGoogle Scholar
  6. 6.
    Lai, J.H., Yuen, P.C., Feng, G.C.: Face recognition using holistic Fourier invariant features. Pattern Recognition 34, 95–109 (2001)zbMATHCrossRefGoogle Scholar
  7. 7.
    Shao, Y., Celenk, M.: Higher-order spectra (HOS) invariants for shape recognition. Pattern Recognition 34, 2097–2113 (2001)zbMATHCrossRefGoogle Scholar
  8. 8.
    Sujan, V.A., Mulqueen, M.P.: Fingerprint identification using space invariant transforms. Pattern Recognition Letters 23, 609–919 (2002)zbMATHCrossRefGoogle Scholar
  9. 9.
    Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press, London (1999)Google Scholar
  10. 10.
    de Vel, O., Aeberhard, S.: Object recognition using random image-lines. Image and Vision Computing 18, 193–198 (2000)CrossRefGoogle Scholar
  11. 11.
    Wood, J.: Invariant pattern recognition: A review. Pattern Recognition 29(1), 1–17 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Tomasz Arodź
    • 1
    • 2
  1. 1.Institute of Computer ScienceAGHKrakówPoland
  2. 2.Academic Computer CentreCYFRONETKrakówPoland

Personalised recommendations