6 search results - page 1 / 2 » Multi-class Binary Object Categorization Using Blurred Shape... |
CIARP
2007
Springer
13 years 10 months ago
2007
Springer
The main difficulty in the binary object classification field lays in dealing with a high variability of symbol appearance. Rotation, partial occlusions, elastic deformations, or...
ICIAP
2009
ACM
14 years 5 months ago
2009
ACM
Multi-class binary symbol classification requires the use of rich descriptors and robust classifiers. Shape representation is a difficult task because of several symbol distortions...
TSMC
2011
12 years 11 months ago
2011
—In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. ...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Many semi-supervised learning algorithms only
deal with binary classification. Their extension to the
multi-class problem is usually obtained by repeatedly
solving a set of bina...
ICIP
2009
IEEE
14 years 5 months ago
2009
IEEE
Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...