Sciweavers

611 search results - page 13 / 123
» Do background images improve
Sort
View
CVPR
2001
IEEE
14 years 9 months ago
A Bayesian Approach to Digital Matting
This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel ...
Yung-Yu Chuang, Brian Curless, David Salesin, Rich...
PR
2006
168views more  PR 2006»
13 years 7 months ago
Adaptive degraded document image binarization
This paper presents a new adaptive approach for the binarization and enhancement of degraded documents. The proposed method does not require any parameter tuning by the user and c...
Basilios Gatos, Ioannis Pratikakis, Stavros J. Per...
CVPR
2010
IEEE
14 years 3 months ago
Fast Polygonal Integration and Its Application in Extending Haar-like Features to Improve Object Detection
The integral image is typically used for fast integrating a function over a rectangular region in an image. We propose a method that extends the integral image to do fast integrat...
Minh-Tri Pham, Viet-Dung Hoang, Tat-Jen Cham, Yang...
ICPR
2010
IEEE
13 years 9 months ago
Human-Area Segmentation by Selecting Similar Silhouette Images Based on Weak-Classifier Response
Human-area segmentation is a major issue in video surveillance. Many existing methods estimate individual human areas from the foreground area obtained by background subtraction, ...
Hiroaki Ando, Hironobu Fujiyoshi
ICIP
2005
IEEE
14 years 1 months ago
3D reconstruction of localized objects from radiographs and based on multiresolution and sparsity
We address the reconstruction of a 3D image from a set of incomplete X-ray tomographic data. In the case where the image is composed of one or several objects lying in a uniform b...
Charles Soussen, Jérôme Idier