Sciweavers

889 search results - page 47 / 178
» Image classification: Classifying distributions of visual fe...
Sort
View
CVPR
2009
IEEE
15 years 2 months ago
Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to se...
Peter V. Gehler, Sebastian Nowozin
CIRA
2007
IEEE
151views Robotics» more  CIRA 2007»
14 years 2 months ago
Image Clustering Using Visual and Text Keywords
Abstract—In classical image classification approaches, lowlevel features have been used. But the high dimensionality of feature spaces poses a challenge in terms of feature selec...
Rajeev Agrawal, Changhua Wu, William I. Grosky, Fa...
IBPRIA
2005
Springer
14 years 1 months ago
Extracting Motion Features for Visual Human Activity Representation
This paper presents a technique to characterize human actions in visual surveillance scenarios in order to describe, in a qualitative way, basic human movements in general imaging ...
Filiberto Pla, Pedro Canotilho Ribeiro, José...
ICMCS
2005
IEEE
138views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Overcomplete ICA-based Manmade Scene Classification
Principal Component Analysis (PCA) has been widely used to extract features for pattern recognition problems such as object recognition. Oliva and Torralba used “spatial envelop...
Matthew Boutell, Jiebo Luo
ICIP
2004
IEEE
14 years 9 months ago
Real-time temporal texture characterisation using block based motion co-occurrence statistics
Contemporary temporal texture classification methods use pixel based features thus making the process slow for time sensitive applications like video indexing and surveillance. In...
Ashfaqur Rahman, M. Manzur Murshed