Sciweavers

Share
ICIP
2001
IEEE

ICA-based probabilistic local appearance models

9 years 12 months ago
ICA-based probabilistic local appearance models
This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are factorized component-wise after an independent component analysis (ICA). Also, we propose a distance-sensitive histograming technique for capturing spatial dependencies. The advantages over existing techniques include the ability to model non-rigid objects (at the expense of modeling accuracy) and the flexibility in modeling spatial relationships. Experiments show that ICA does improve modeling accuracy and detection performance. Experiments in object detection in cluttered scenes have demonstrated promising results.
Xiang Sean Zhou, Baback Moghaddam, Thomas S. Huang
Added 25 Oct 2009
Updated 27 Oct 2009
Type Conference
Year 2001
Where ICIP
Authors Xiang Sean Zhou, Baback Moghaddam, Thomas S. Huang
Comments (0)
books