Advertisement

Local Phase Quantization for Blur Insensitive Texture Description

  • Janne Heikkilä
  • Esa Rahtu
  • Ville Ojansivu
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 506)

Abstract

Blur is one of the most common sources of image quality degradations, and it appears very often in practical photography. Most often blur is a result of misfocused optics, changes in the camera pose, and movements in the scene. Beyond the impaired visual quality, blurring may cause severe complications to computer vision algorithms, particularly in texture analysis. These problems have been tackled using deblurring approaches, which ultimately leads to much harder intermediate problem versus the original task of texture characterization. In this chapter, we present a simple yet powerful texture descriptor that is, by design, tolerant to most common types of image blurs. The proposed approach is based on quantizing the phase information of the local Fourier transform, which leads to computationally efficient and compact feature representation. We show how to construct several variants of our descriptor including rotation invariance and dynamic texture representation. Moreover, we present texture classification experiments, which illustrate the behavior under several different blur configurations. Surprisingly, the descriptor also achieves state-of-the-art performance with sharp textures, although the main design criteria was tolerance to blur.

Keywords

Point Spread Function Local Binary Pattern Gabor Filter Phase Spectrum Motion Blur 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

This work was partially supported by Academy of Finland (Grant no. 127702). Authors would like to thank Mr. Veli Juhani Päivärinta for providing his material to this chapter.

References

  1. 1.
    Ojala, T., Pietikäinen, M., Mäenpää, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)CrossRefGoogle Scholar
  2. 2.
    Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. In: Proceedings of Analysis and Modeling of Faces and Gestures (2007)Google Scholar
  3. 3.
    Varma, M., Zisserman, A.: Classifying images of materials: achieving viewpoint and illumination independence. In: Proceedings of European Conference on Computer Vision, vol. 3, pp. 255–271 (2002)Google Scholar
  4. 4.
    Varma, M., Zisserman, A.: A statistical approach to material classification using image patch exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 2032–2047 (2009)CrossRefGoogle Scholar
  5. 5.
    Flusser, J., Suk, T.: Degraded image analysis: an invariant approach. IEEE Trans. Pattern Anal. Mach. Intell. 20(6), 590–603 (1998)CrossRefGoogle Scholar
  6. 6.
    Zhang, H., Shu, H., Han, G., Coatrieux, G., Luo, L., Coatrieux, J.: Blurred image recognition by Legendre moment invariants. IEEE Trans. Image Process. 19(3), 596–611 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Ojansivu, V., Heikkilä, J.: A method for blur and similarity transform invariant object recognition. In: Proceedings of International Conference on Image Analysis and Processing, pp. 583–588 (2007)Google Scholar
  8. 8.
    van de Weijer, J., Schmid, C.: Blur robust and color constant image description. In: Proceedings of IEEE International Conference on Image Processing, pp. 993–996 (2006)Google Scholar
  9. 9.
    Granlund, G., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic, Boston (1995)CrossRefGoogle Scholar
  10. 10.
    Zhang, L., Zhang, L., Guo, Z., Zhang, D.: Monogenic-LBP: a new approach for rotation invariant texture classification. In: Proceedings of International Conference on Image Processing, pp. 2677–2680 (2010)Google Scholar
  11. 11.
    Zhang, B., Shan, S., Chen, X., Gao, W.: Histogram of Gabor phase patterns (HGPP): a novel object representation approach for face recognition. IEEE Trans. Image Process. 16(1), 57–68 (2007)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Fischer, S., Bigun, J.: Texture boundary tracking with gabor phase. In: Borgefors, G. (ed.)Theory and Applications of Image Analysis II, pp. 101–112. World Scientific, Singapore (1995)Google Scholar
  13. 13.
    Zhou, F., Feng, J., Shi, Q.: Texture feature based on local Fourier transform. In: Proceedings of International Conference on Image Processing, pp. 610–613 (2001)Google Scholar
  14. 14.
    Zhao, G., Pietikäinen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 915–928 (2007)CrossRefGoogle Scholar
  15. 15.
    Ojansivu, V., Heikkilä, J.: Blur insensitive texture classification using local phase quantization. In: Proceedings of International Conference on Image and Signal Processing, pp. 236–243 (2008)Google Scholar
  16. 16.
    Heikkilä, J., Ojansivu, V.: Methods for local phase quantization in blur-insensitive image analysis. In: Proceedings of International Workshop on Local and Non-Local Approximation in Image Processing, pp. 104–111 (2009)Google Scholar
  17. 17.
    Ojansivu, V., Rahtu, E., Heikkilä, J.: Rotation invariant blur insensitive texture analysis using local phase quantization. In: Proceedings of 19th International Conference on Pattern Recognition, 4 p (2008)Google Scholar
  18. 18.
    Rahtu, E., Heikkilä, J., Ojansivu, V., Ahonen, T.: Local phase quantization for blur-insensitive image analysis. Image Vis. Comput. 30(8), 501–512 (2012)Google Scholar
  19. 19.
    Päivärinta, V.J., Rahtu, E., Heikkilä, J.: Volume local phase quantization for blur-insensitive dynamic texture classification. In: Proceedings of Scandinavian Conference on Image, Analysis, pp. 360–369 (2011)Google Scholar
  20. 20.
    Hadid, A., Nishiyama, M., Sato, Y.: Recognition of blurred faces via facial deblurring combined with blur-tolerant descriptors. In: Proceedings of International Conference on Pattern Recognition, pp. 1160–1163 (2010)Google Scholar
  21. 21.
    Nishiyama, M., Hadid, A., Takeshima, H., Shotton, J., Kozakaya, T., Yamaguchi, O.: Facial deblur inference using subspace analysis for recognition of blurred faces. IEEE Trans. Pattern Anal. Mach. Intell. 33(4), 838–845 (2011)CrossRefGoogle Scholar
  22. 22.
    Chan, C.H., Tahir, M., Kittler, J., Pietikäinen, M.: Multiscale local phase quantisation for robust component-based face recognition using kernel fusion of multiple descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1164–1177 (2013)Google Scholar
  23. 23.
    Jiang, B., Valstar, M.F., Pantic, M.: Action unit detection using sparse appearance descriptors in space-time video volumes. In: Proceedings of IEEE Conference on Automatic Face and Gesture Recognition, pp. 314–321 (2011)Google Scholar
  24. 24.
    Brahnam, S., Nanni, L., Shi, J.Y., Lumini, A.: Local phase quantization texture descriptor for protein classification. In: Proceedings of International Conference on Bioinformatics and Computational Biology (2010)Google Scholar
  25. 25.
    Banham, M., Katsaggelos, A.: Digital image restoration. IEEE Signal Process. Mag. 14(2), 24–41 (1997)CrossRefGoogle Scholar
  26. 26.
    Wang, Z., Simoncelli, E.P., Local phase coherence and the perception of blur. In: Proceedings of Advances in Neural Information Processing Systems, pp. 786–792 (2003)Google Scholar
  27. 27.
    Boukerroui, D., Noble, J., Brady, M.: On the choice of band-pass quadrature filters. J. Math. Imaging Vis. 21, 53–80 (2004)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Felsberg, M., Sommer, G.: The monogenic signal. IEEE Trans. Signal Process. 49(12), 3136–3144 (2001)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Manjunathi, B., Ma, W.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18(8), 837–842 (1996)CrossRefGoogle Scholar
  30. 30.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Int. J. Comput. Vis. 62(1), 61–81 (2005)Google Scholar
  31. 31.
    Crosier, M., Griffin, L.D.: Using basic image features for texture classification. Int. J. Comput. Vis. 88(3), 447–460 (2010)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.: Understanding and evaluating blind deconvolution algorithms. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1964–1971 (2009)Google Scholar
  33. 33.
    Ahonen, T., Matas, J., He, C., Pietikäinen, M.: Rotation invariant image description with local binary pattern histogram Fourier features. In: Proceedings of Scandinavian Conference on Image, Analysis, pp. 61–70 (2009)Google Scholar
  34. 34.
    Ghanem, B., Ahuja, N.: Maximum margin distance learning for dynamic texture recognition. In: Proceedings of European Conference on Computer Vision, pp. 223–236 (2010)Google Scholar
  35. 35.
    Péteri, R., Fazekas, S., Huiskes, M.J.: DynTex: a comprehensive database of dynamic textures. Pattern Recogn. Lett. 31(12), 1627–1632 (2010). http://www.cwi.nl/projects/dyntex/

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Center for Machine Vision ResearchUniversity of OuluOuluFinland
  2. 2.Institute for Molecular Medicine Finland FIMMHelsinkiFinland

Personalised recommendations