Advertisement

Keypoint Recognition Using Random Forests and Random Ferns

  • V. Lepetit
  • P. Fua
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

In many 3D object detection and pose estimation problems, run-time performance is of critical importance. However, there usually is time to train the system. We introduce an approach that takes advantage of this fact by formulating the wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem. This shifts much of the computational burden to a training phase and eliminates the need for expensive patch preprocessing, without sacrificing recognition performance. This makes our approach highly suitable for real-time operations on low-powered devices.

To this end, we developed two related methods. The first uses random forests that rely on simple binary tests on image intensities surrounding the keypoints. In the second, we flatten the trees to turn them into simple bit strings, which we will refer to as ferns, and combine their output in a Naïve Bayesian manner. Surprisingly, the ferns, while simpler, actually perform better than the trees. This is because the Naïve Bayesian approach benefits more from the thousands of synthetic training examples we can generate than output averaging as usually performed by decision forests. Furthermore, the more general partition that the trees allow does not appear to be of great use for our problem. Parts of this chapter are reprinted, with permission, from Lepetit, Lagger, and Fua, Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (2005), © 2005 IEEE.

Keywords

Random Forest Recognition Rate Training Image Interest Point Image Patch 
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.

References

  1. 5.
    Amit Y, Geman D (1997) Shape quantization and recognition with randomized trees. Neural Comput 9(7) Google Scholar
  2. 21.
    Beis J, Lowe DG (1997) Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In: Proc IEEE conf computer vision and pattern recognition (CVPR) Google Scholar
  3. 28.
    Bishop CM (2006) Pattern recognition and machine learning. Springer, New York Google Scholar
  4. 92.
    Domingos P, Pazzani M, Provan G (1997) On the optimality of the simple Bayesian classifier under zero-one loss. Mach Learn Google Scholar
  5. 116.
    Friedman JH, Fayyad U (1997) On bias, variance, 0/1-loss, and the curse-of-dimensionality. Data Min Knowl Discov 1 Google Scholar
  6. 128.
    Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 36(1) Google Scholar
  7. 163.
    Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14 Google Scholar
  8. 168.
    Hoiem D, Sukthankar R, Schneiderman H, Huston L (2004) Object-based image retrieval using the statistical structure of images. J Mach Learn Res 02 Google Scholar
  9. 214.
    Lepetit V, Lagger P, Fua P (2005) Randomized trees for real-time keypoint recognition. In: Proc IEEE conf computer vision and pattern recognition (CVPR) Google Scholar
  10. 225.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2) Google Scholar
  11. 249.
    Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, van Gool L (2005) A comparison of affine region detectors. Int J Comput Vis 65(1/2) Google Scholar
  12. 280.
    Ozuysal M, Calonder M, Lepetit V, Fua P (2010) Fast keypoint recognition using random ferns. IEEE Trans Pattern Anal Mach Intell 32(3) Google Scholar
  13. 357.
    Strecha C, Fransens R, van Gool L (2006) Combined depth and outlier estimation in multi-view stereo. In: Proc IEEE conf computer vision and pattern recognition (CVPR) Google Scholar
  14. 418.
    Zheng F, Webb GI (2005) A comparative study of semi-naïve Bayes methods in classification learning. In: Australasian data mining conference Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • V. Lepetit
    • 1
  • P. Fua
    • 1
  1. 1.Ecole Polytechnique Fédérale de LausanneLausanneSwitzerland

Personalised recommendations