Sciweavers

ICDAR
2009
IEEE
13 years 11 months ago
A Novel Feature Extraction and Classification Methodology for the Recognition of Historical Documents
In this paper, we present a methodology for off-line character recognition that mainly focuses on handling the difficult cases of historical fonts and styles. The proposed methodo...
Georgios Vamvakas, Basilios Gatos, Stavros J. Pera...
ICML
2008
IEEE
14 years 5 months ago
Dirichlet component analysis: feature extraction for compositional data
We consider feature extraction (dimensionality reduction) for compositional data, where the data vectors are constrained to be positive and constant-sum. In real-world problems, t...
Hua-Yan Wang, Qiang Yang, Hong Qin, Hongbin Zha
ICIP
2005
IEEE
14 years 6 months ago
Feature extraction of non-stained melanocyte cells
We present a procedure that extracts detailed morphological measurements from human melanocyte cells. The cells and imaging condition have the following characteristics: (i) no im...
Ralf Kemkemer, Giovanni G. Estrada, D. Kaufmann, D...
CVPR
2008
IEEE
14 years 6 months ago
On the use of independent tasks for face recognition
We present a method for learning discriminative linear feature extraction using independent tasks. More concretely, given a target classification task, we consider a complementary...
Àgata Lapedriza, David Masip, Jordi Vitri&a...
CVPR
2008
IEEE
14 years 6 months ago
Integrated feature selection and higher-order spatial feature extraction for object categorization
In computer vision, the bag-of-visual words image representation has been shown to yield good results. Recent work has shown that modeling the spatial relationship between visual ...
David Liu, Gang Hua, Paul A. Viola, Tsuhan Chen
CVPR
2004
IEEE
14 years 6 months ago
Shaping Receptive Fields for Affine Invariance
The Gaussian kernel has played a central role in multi-scale methods for feature extraction and matching. In this paper, a method for shaping the filter using the local image stru...
S. Ravela
ICCV
2009
IEEE
1611views Computer Vision» more  ICCV 2009»
14 years 9 months ago
Packing bag-of-features
One of the main limitations of image search based on bag-of-features is the memory usage per image. Only a few million images can be handled on a single machine in rea- sonable ...
Herve Jegou, Matthijs Douze, Cordelia Schmid
CVPR
2009
IEEE
14 years 11 months ago
On the burstiness of visual elements
Burstiness, a phenomenon initially observed in text re- trieval, is the property that a given visual element appears more times in an image than a statistically independent mode...
Herve Jegou (INRIA), Matthijs Douze (INRIA), Corde...
CVPR
2009
IEEE
1599views Computer Vision» more  CVPR 2009»
14 years 11 months ago
Multi-Label Sparse Coding for Automatic Image Annotation
In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is ...
Changhu Wang (University of Science and Technology...