CLOR
2006
14 years 2 months ago
2006
This chapter presents an approach for texture and object recognition that uses scale- or affine-invariant local image features in combination with a discriminative classifier. Text...
ECCV
2010
Springer
14 years 4 months ago
2010
Springer
We present a data-driven approach to predict the importance of edges and construct a Markov network for image analysis based on statistical models of global and local image feature...
WACV
2005
IEEE
14 years 4 months ago
2005
IEEE
Many existing systems for human body tracking are based on dynamic model-based tracking that is driven by local image features. Alternatively, within a view-based approach, tracki...
CVPR
2005
IEEE
14 years 4 months ago
2005
IEEE
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase feature [3]) in terms of their distinctiveness, detectability, and robustness to i...
ICML
2009
IEEE
14 years 11 months ago
2009
IEEE
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
ICPR
2004
IEEE
14 years 12 months ago
2004
IEEE
We propose a novel approach to improve the distinctiveness of local image features without significantly affecting their robustness with respect to image deformations. Local image...
ICIP
2006
IEEE
15 years 15 days ago
2006
IEEE
The ability to automatically detect visually interesting regions in images has practical applications in the design of active machine vision systems. Analysis of the statistics of...
ICIP
2008
IEEE
15 years 17 days ago
2008
IEEE
We demonstrate that it is possible to filter an image with an elliptic window of varying size, elongation and orientation with a fixed computational cost per pixel. Our method inv...
ICCV
1999
IEEE
15 years 23 days ago
1999
IEEE
Proc. of the International Conference on Computer Vision, Corfu (Sept. 1999) An object recognition system has been developed that uses a new class of local image features. The fea...