Sciweavers

835 search results - page 15 / 167
» Optimal Linear Representations of Images for Object Recognit...
Sort
View
MM
2004
ACM
219views Multimedia» more  MM 2004»
14 years 2 months ago
Multi-level annotation of natural scenes using dominant image components and semantic concepts
Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...
Jianping Fan, Yuli Gao, Hangzai Luo
SCIA
2007
Springer
114views Image Analysis» more  SCIA 2007»
14 years 2 months ago
Object Recognition Using Frequency Domain Blur Invariant Features
In this paper, we propose novel blur invariant features for the recognition of objects in images. The features are computed either using the phase-only spectrum or bispectrum of th...
Ville Ojansivu, Janne Heikkilä
CVPR
2000
IEEE
14 years 10 months ago
Reconstruction of a Scene with Multiple Linearly Moving Objects
We describe an algorithmfor reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the mo...
Mei Han, Takeo Kanade
ICIP
2003
IEEE
14 years 1 months ago
ICA and Gabor representation for facial expression recognition
Two hybrid systems for classifying seven categories of human facial expression are proposed. The £rst system combines independent component analysis (ICA) and support vector mach...
Ioan Buciu, Constantine Kotropoulos, Ioannis Pitas
CVPR
2008
IEEE
13 years 8 months ago
Joint learning and dictionary construction for pattern recognition
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
Duc-Son Pham, Svetha Venkatesh