A Novel Image Descriptor Based on Anisotropic Filtering

  • Darshan VenkatrayappaEmail author
  • Philippe Montesinos
  • Daniel Diep
  • Baptiste Magnier
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9256)


In this paper, we present a new image patch descriptor for object detection and image matching. The descriptor is based on the standard HoG pipeline. The descriptor is generated in a novel way, by embedding the response of an oriented anisotropic derivative half Gaussian kernel in the Histogram of Orientation Gradient (HoG) framework. By doing so, we are able to bin more curvature information. As a result, our descriptor performs better than the state of art descriptors such as SIFT, GLOH and DAISY. In addition to this, we repeat the same procedure by replacing the anisotropic derivative half Gaussian kernel with a computationally less complex anisotropic derivative half exponential kernel and achieve similar results. The proposed image descriptors using both the kernels are very robust and shows promising results for variations in brightness, scale, rotation, view point, blur and compression. We have extensively evaluated the effectiveness of the devised method with various challenging image pairs acquired under varying circumstances.


Anisotropic half derivative gaussian kernel Anisotropic half derivative exponential kernel Image descriptor HoG Image matching 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This work is funded by L’institut mediterraneen des metiers de la longevite (I2ML), Nimes, France.


  1. 1.
    Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision (IJCV) 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE Trans. Pattern Anal. Mach. Intell., 1615–1630 (2005)Google Scholar
  3. 3.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.J.: Speeded-up robust features. In: Computer Vision and Image Understanding, vol. 110, pp. 346–359 (2008)Google Scholar
  4. 4.
    Wang, Z., Fan, B., Wu, F.: Local intensity order pattern for feature description. In: IEEE International Conference on Computer Vision (ICCV), pp. 603–610, November 2011Google Scholar
  5. 5.
    Morel, J.M., Yu, G.: ASIFT: A New Framework for Fully Affine Invariant Image Comparison. Journal on Imaging Sciences 2, 438–469 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Tola, E., Lepetit, V., Fua, P.: DAISY: An Efficient Dense Descriptor Applied to Wide Baseline Stereo. TPAMI 32, 815–830 (2010)CrossRefGoogle Scholar
  7. 7.
    Dalal, N., Triggs, T.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 886–893 (2005)Google Scholar
  8. 8.
    Schmid, C., Mohr, R.: Local Gray-value Invariants for Image Retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 9, 530–535 (1997)CrossRefGoogle Scholar
  9. 9.
    Koenderink, J.J., Van Doorn, A.J.: Representation of local geometry in the visual system. Biological Cybernetics 55, 367–375 (1987)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Larsen, A.B.L., Darkner, S., Dahl, A.L., Pedersen, K.S.: Jet-based local image descriptors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 638–650. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  11. 11.
    Palomares, J.L., Montesinos, P., Diep, D.: A new affine invariant method for image matching. In: 3DIP Image Processing and Applications, vol. 8290 (2012)Google Scholar
  12. 12.
    Monroy, A., Eigenstetter, A., Ommer, B.: Beyond straight lines - object detection using curvature. In: ICIP, pp. 3561–3564 (2011)Google Scholar
  13. 13.
    Zitnick, C.L.: Binary coherent edge descriptors. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 170–182. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  14. 14.
    Eigenstetter, A., Ommer, B.: Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity, Curran Associates, Inc. (2012)Google Scholar
  15. 15.
    Magnier, B., Montesinos, P.: Evolution of image regularization with PDEs toward a new anisotropic smoothing based on half kernels. In: SPIE, Image Processing: Algorithms and Systems XI (2013)Google Scholar
  16. 16.
    Montesinos, P., Magnier, B.: A new perceptual edge detector in color images. In: Blanc-Talon, J., Bone, D., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2010, Part I. LNCS, vol. 6474, pp. 209–220. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  17. 17.
    Deriche, R.: Recursively implementing the gaussian and its derivatives. In: ICIP, pp. 263–267 (1992)Google Scholar
  18. 18.
    Shen, J., Castan, S.: An optimal linear operator for step edge detection. Graphical Model and Image Processing (CVGIP) 54, 112–133 (1992)CrossRefGoogle Scholar
  19. 19.
    Mikolajczyk, K., Schmid, C.: Scale & Affine Invariant Interest Point Detectors. International Journal of Computer Vision (IJCV) 60, 63–86 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Darshan Venkatrayappa
    • 1
    Email author
  • Philippe Montesinos
    • 1
  • Daniel Diep
    • 1
  • Baptiste Magnier
    • 1
  1. 1.LGI2P - Ecole des Mines D’AlesNimesFrance

Personalised recommendations