Sciweavers

3 search results - page 1 / 1
» Off-line Handwritten Textline Recognition Using a Mixture of...
Sort
View
ICPR
2004
IEEE
14 years 6 months ago
Off-line Handwritten Textline Recognition Using a Mixture of Natural and Synthetic Training Data
In this paper the problem of off-line handwritten cursive text recognition is considered. A method for expanding the set of available training textlines by applying random perturb...
Tamás Varga, Horst Bunke
ICDAR
2005
IEEE
13 years 10 months ago
Distinguishing Mathematics Notation from English Text using Computational Geometry
A trainable method for distinguishing between mathematics notation and natural language (here, English) in images of textlines, using computational geometry methods only with no a...
Derek M. Drake, Henry S. Baird
CVPR
2005
IEEE
14 years 7 months ago
Part-Based Statistical Models for Object Classification and Detection
We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in the...
Elliot Joel Bernstein, Yali Amit