Towards Recognizing Feature Points using Classification Trees

  title={Towards Recognizing Feature Points using Classification Trees},
  author={Vincent. Lepetit and Pascal. Fua},
In earlier work [Lepetit et al., 2004], we proposed to treat wide baseline matching of feature points as a classification problem and proposed an implementation based on K-means and nearest neighbor classification. We showed that this method is both reliable and faster than competing methods, but still too slow for real-time implementations. Here we show that using decision trees instead speeds up the computation greatly, while increasing the robustness. This allows point matching under large… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 16 extracted citations

Fast object recognition based on corner geometric relationship

Proceedings of SICE Annual Conference 2010 • 2010
View 4 Excerpts
Highly Influenced

A Linear Estimation of the Face's Tridimensional Pose and Facial Expressions

C Mme.Alice, APLIER, +8 authors Michel Franck
View 5 Excerpts
Highly Influenced

Teaching a robot to operate a lift

2008 10th International Conference on Control, Automation, Robotics and Vision • 2008
View 4 Excerpts
Highly Influenced

Smart IDReader: Document Recognition in Video Stream

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) • 2017
View 1 Excerpt

Adaptation of the object recognition method based on random ferns for mobile robots

2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA) • 2016
View 1 Excerpt

Kinsight: Localizing and Tracking Household Objects Using Depth-Camera Sensors

2012 IEEE 8th International Conference on Distributed Computing in Sensor Systems • 2012
View 1 Excerpt

Multi-robot exploration framework using robot vision and laser range data

2011 IEEE/SICE International Symposium on System Integration (SII) • 2011
View 1 Excerpt

Target acquisition using Natural Feature Image Recognition

2009 IEEE Aerospace conference • 2009
View 2 Excerpts

Feature selection for real-time image matching systems

2008 19th International Conference on Pattern Recognition • 2008
View 2 Excerpts


Publications referenced by this paper.
Showing 1-10 of 21 references


V. Lepetit, J. Pilet, P. Fua. Point Matching as a Classification Problem fo Fast, Robust Object Pose Estimation. In CVPR, Washington
June • 2004
View 3 Excerpts
Highly Influenced


Cordelia Schmid, Roger Mohr. Local grayvalue invariants for image retriev Analysis, Machine Intelligence
May • 1997
View 3 Excerpts
Highly Influenced

International Journal of Computer Vision

David G. Lowe. Distinctive Image Features from Scale-Inv Keypoints
20(2):91–110, • 2004
View 2 Excerpts

Point matching as a classification problem for fast and robust object pose estimation

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. • 2004

pages 128–142

K. Mikolajczyk, C. Schmid. An affine invariant interest point detecto Vision
Springer, • 2002
View 2 Excerpts


Franois Fleuret, Donald Geman. Coarse-to-fine visual selection. Internatio Vision
January • 2001

Similar Papers

Loading similar papers…