Hierarchical organization of appearance-based parts and relations for object recognition

被引：11

作者：

Camps, OI ^{[1
]}

Huang, CY ^{[1
]}

Kanungo, T ^{[1
]}

机构：

[1] Penn State Univ, Dept Elect Engn, University Pk, PA 16802 USA

来源：

1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS | 1998年

关键词：

object representation; object recognition; appearance-based methods; shape classification;

D O I：

10.1109/CVPR.1998.698678

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In [2] a new object representation using appearance-based parts and relations to recognize 3D objects from 2D images, in the presence of occlusion and background clutter was introduced. 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 eigenspaces spanned by the parts and the relations. In this paper we introduce the discriminatory power of the proposed features and describe how to use it to organize large databases of objects.

引用

页码：685 / 691

页数：7