KAZE Features

  • Pablo Fernández Alcantarilla
  • Adrien Bartoli
  • Andrew J. Davison
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7577)

Abstract

In this paper, we introduce KAZE features, a novel multiscale 2D feature detection and description algorithm in nonlinear scale spaces. Previous approaches detect and describe features at different scale levels by building or approximating the Gaussian scale space of an image. However, Gaussian blurring does not respect the natural boundaries of objects and smoothes to the same degree both details and noise, reducing localization accuracy and distinctiveness. In contrast, we detect and describe 2D features in a nonlinear scale space by means of nonlinear diffusion filtering. In this way, we can make blurring locally adaptive to the image data, reducing noise but retaining object boundaries, obtaining superior localization accuracy and distinctiviness. The nonlinear scale space is built using efficient Additive Operator Splitting (AOS) techniques and variable conductance diffusion. We present an extensive evaluation on benchmark datasets and a practical matching application on deformable surfaces. Even though our features are somewhat more expensive to compute than SURF due to the construction of the nonlinear scale space, but comparable to SIFT, our results reveal a step forward in performance both in detection and description against previous state-of-the-art methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Liu, C., Yuen, J., Torralba, A.: Dense scene alignment using SIFT flow for object recognition. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2009)Google Scholar
  2. 2.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR (2006)Google Scholar
  3. 3.
    Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building Rome in a Day. In: Intl. Conf. on Computer Vision, ICCV, Kyoto, Japan (2009)Google Scholar
  4. 4.
    Koenderink, J.: The structure of images. Biological Cybernetics 50, 363–370 (1984)MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Lindeberg, T.: Feature detection with automatic scale selection. Intl. J. of Computer Vision 30, 77–116 (1998)Google Scholar
  6. 6.
    Duits, R., Florack, L., De Graaf, J., ter Haar Romeny, B.: On the axioms of scale space theory. Journal of Mathematical Imaging and Vision 20, 267–298 (2004)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Perona, P., Malik, J.: Scale-space and edge detection using annisotropic diffusion. IEEE Trans. Pattern Anal. Machine Intell. 12, 1651–1686 (1990)CrossRefGoogle Scholar
  8. 8.
    Álvarez, L., Lions, P., Morel, J.: Image selective smoothing and edge detection by nonlinear diffusion. SIAM Journal on Numerical Analysis (SINUM) 29, 845–866 (1992)MATHCrossRefGoogle Scholar
  9. 9.
    Weickert, J., ter Haar Romeny, B., Viergever, M.A.: Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Trans. Image Processing 7 (1998)Google Scholar
  10. 10.
    ter Haar Romeny, B.M.: Front-End Vision and Multi-Scale Image Analysis. Multi-Scale Computer Vision Theory and Applications, written in Mathematica. Kluwer Academic Publishers (2003)Google Scholar
  11. 11.
    Weickert, J.: Efficient image segmentation using partial differential equations and morphology. Pattern Recognition 34, 1813–1824 (2001)MATHCrossRefGoogle Scholar
  12. 12.
    Qiu, Z., Yang, L., Lu, W.: A new feature-preserving nonlinear anisotropic diffusion method for image denoising. In: British Machine Vision Conf., BMVC, Dundee, UK (2011)Google Scholar
  13. 13.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. Intl. J. of Computer Vision 65, 43–72 (2005)CrossRefGoogle Scholar
  14. 14.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Machine Intell. 27, 1615–1630 (2005)CrossRefGoogle Scholar
  15. 15.
    Weickert, J., Ishikawa, S., Imiya, A.: Linear scale-space has first been proposed in Japan. Journal of Mathematical Imaging and Vision 10 (1999)Google Scholar
  16. 16.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Intl. J. of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  17. 17.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. Computer Vision and Image Understanding 110, 346–359 (2008)CrossRefGoogle Scholar
  18. 18.
    Viola, P., Jones, M.J.: Robust real-time face detection. Intl. J. of Computer Vision 57, 137–154 (2004)CrossRefGoogle Scholar
  19. 19.
    Agrawal, M., Konolige, K., Blas, M.R.: CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 102–115. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  20. 20.
    Brown, M., Lowe, D.: Invariant features from interest point groups. In: British Machine Vision Conf., BMVC, Cardiff, UK (2002)Google Scholar
  21. 21.
    Weickert, J., Scharr, H.: A scheme for coherence-enhancing diffusion filtering with optimized rotation invariance. Journal of Visual Communication and Image Representation 13, 103–118 (2002)CrossRefGoogle Scholar
  22. 22.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
  23. 23.
    Pizarro, D., Bartoli, A.: Feature-based deformable surface detection with self-occlusion reasoning. Intl. J. of Computer Vision 97, 54–70 (2012)MATHCrossRefGoogle Scholar
  24. 24.
    Salzmann, M., Hartley, R., Fua, P.: Convex optimization for deformable surface 3D tracking. In: Intl. Conf. on Computer Vision, ICCV, Rio de Janeiro, Brazil (2007)Google Scholar
  25. 25.
    Bartoli, A., Gérard, Y., Chadebecq, F., Collins, T.: On template-based reconstruction from a single view: Analytical solutions and proofs of well-posedness for developable, isometric and conformal surfaces. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pablo Fernández Alcantarilla
    • 1
  • Adrien Bartoli
    • 1
  • Andrew J. Davison
    • 2
  1. 1.ISIT-UMR 6284 CNRSUniversité d’AuvergneClermont FerrandFrance
  2. 2.Department of ComputingImperial College LondonUK

Personalised recommendations