Probabilistic Geometric Grammars for Object Recognition by

  title={Probabilistic Geometric Grammars for Object Recognition by},
  author={Margaret Aida Aycinena},
  • Margaret Aida Aycinena
  • Published 2005
This thesis presents a generative three-dimensional (3D) representation and recognition framework for classes of objects. The framework uses probabilistic grammars to represent object classes recursively in terms of their parts, thereby exploiting the hierarchical and substitutive structure inherent to many types of objects. The framework models the 3D geometric characteristics of object parts using multivariate conditional Gaussians over dimensions, position, and rotation. I present algorithms… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 32 references

An Introduction to Probabilistic Graphical Models

M. I. Jordan
View 4 Excerpts
Highly Influenced

Exploiting Quaternions to Support Expressive Interactive Character Motion

Michael Patrick Johnson
PhD thesis, Massachusetts Institute of Technology, • 2003
View 10 Excerpts
Highly Influenced

Natural language understanding

Bejnamin/Cummings series in computer science • 1987
View 11 Excerpts
Highly Influenced

Differing views on views: response to Hayward and Tarr (2000)

Vision Research • 2000
View 7 Excerpts
Highly Influenced

Foundations of Statistical Natural Language Processing

Computational Linguistics • 2000
View 4 Excerpts
Highly Influenced

The Quickhull Algorithm for Convex Hulls

ACM Trans. Math. Softw. • 1996
View 10 Excerpts
Highly Influenced

Spatial priors for part-based recognition using statistical models

2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) • 2005
View 2 Excerpts

Similar Papers

Loading similar papers…