Sciweavers

286 search results - page 32 / 58
» Processing images and video for an impressionist effect
Sort
View
ICASSP
2011
IEEE
14 years 1 months ago
Detecting moving objects from dynamic background with shadow removal
Background subtraction is commonly used to detect foreground objects in video surveillance. Traditional background subtraction methods are usually based on the assumption that the...
Shih-Chieh Wang, Te-Feng Su, Shang-Hong Lai
FGR
2006
IEEE
255views Biometrics» more  FGR 2006»
15 years 1 months ago
Incremental Kernel SVD for Face Recognition with Image Sets
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such...
Tat-Jun Chin, Konrad Schindler, David Suter
65
Voted
TCSV
2008
124views more  TCSV 2008»
14 years 9 months ago
A Block-Edge-Pattern-Based Content Descriptor in DCT Domain
In this correspondence, we describe a robust and effective content descriptor based on block edge patterns extracted directly in DCT domain, which is suitable for applications in J...
Jianmin Jiang, Kaijin Qiu, Guoqiang Xiao
ICIP
2005
IEEE
15 years 11 months ago
Tracking and segmenting people with occlusions by a sample consensus based method
One of the most difficult issues in visual tracking is to track people in groups, especially under occlusions. In this paper, we present a novel sample consensus based method, whi...
Hanzi Wang, David Suter
ICIP
2009
IEEE
15 years 10 months ago
Recognizing Human Actions By Fusing Spatio-temporal Appearance And Motion Descriptors
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent...