|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97)
Object Recognition Using Appearance-Based Parts and Relations
Puerto Rico
June 17-June 19
ISBN: 0-8186-7822-4
| ASCII Text | x | ||
| Chien-Yuan Huang, Octavia I. Camps, Tapas Kanungo, "Object Recognition Using Appearance-Based Parts and Relations," 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 877, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97), 1997. | |||
| BibTex | x | ||
| @article{ 10.1109/CVPR.1997.609431, author = {Chien-Yuan Huang and Octavia I. Camps and Tapas Kanungo}, title = {Object Recognition Using Appearance-Based Parts and Relations}, journal ={2012 IEEE Conference on Computer Vision and Pattern Recognition}, volume = {0}, year = {1997}, issn = {1063-6919}, pages = {877}, doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.1997.609431}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - 2012 IEEE Conference on Computer Vision and Pattern Recognition TI - Object Recognition Using Appearance-Based Parts and Relations SN - 1063-6919 SP EP A1 - Chien-Yuan Huang, A1 - Octavia I. Camps, A1 - Tapas Kanungo, PY - 1997 KW - Object representation KW - object recognition KW - MDL segmentation KW - appearance-based representation. VL - 0 JA - 2012 IEEE Conference on Computer Vision and Pattern Recognition ER - | |||
The recognition of general three-dimensional objects in cluttered scenes is a challenging problem. In particular, the design of a good representation suitable to model large numbers of generic objects that is also robust to occlusion has been an stumbling block in achieving success. In this paper, we propose a representation using appearance-based parts and relations to overcome these problems. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained from collection of images and compactly represented by parametric manifolds in the two eigenspaces spanned by the parts and the relations.
Index Terms:
Object representation, object recognition, MDL segmentation, appearance-based representation.
Citation:
Chien-Yuan Huang, Octavia I. Camps, Tapas Kanungo, "Object Recognition Using Appearance-Based Parts and Relations," cvpr, pp.877, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97), 1997
Usage of this product signifies your acceptance of the Terms of Use.