Sciweavers

40 search results - page 5 / 8
» Discriminative codeword selection for image representation
Sort
View
ICDAR
2011
IEEE
13 years 9 months ago
Continuous CRF with Multi-scale Quantization Feature Functions Application to Structure Extraction in Old Newspaper
—We introduce quantization feature functions to represent continuous or large range discrete data into the symbolic CRF data representation. We show that doing this convertion in...
David Hebert, Thierry Paquet, Stéphane Nico...
NIPS
2004
14 years 11 months ago
Learning Hyper-Features for Visual Identification
We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular in...
Andras Ferencz, Erik G. Learned-Miller, Jitendra M...
CVPR
2009
IEEE
16 years 4 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
PAMI
2006
132views more  PAMI 2006»
14 years 9 months ago
Capitalize on Dimensionality Increasing Techniques for Improving Face Recognition Grand Challenge Performance
This paper presents a novel pattern recognition framework by capitalizing on dimensionality increasing techniques. In particular, the framework integrates Gabor image representatio...
Chengjun Liu
ICIP
2000
IEEE
15 years 11 months ago
Perceptible Level Lines and Isoperimetric Ratio
This paper introduces a simple criterion to select the most important level lines from the numerous set obtained with a topographic map. A topographic map gives a morphological an...
Jacques Froment