Sciweavers

100 search results - page 1 / 20
» Co-training for Handwritten Word Recognition
Sort
View
ICDAR
2011
IEEE
12 years 4 months ago
Co-training for Handwritten Word Recognition
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
Volkmar Frinken, Andreas Fischer, Horst Bunke, Ali...
IJSI
2008
156views more  IJSI 2008»
13 years 4 months ago
Co-Training by Committee: A Generalized Framework for Semi-Supervised Learning with Committees
Many data mining applications have a large amount of data but labeling data is often difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supe...
Mohamed Farouk Abdel Hady, Friedhelm Schwenker
ICPR
2008
IEEE
13 years 11 months ago
A novel orientation free method for online unconstrained cursive handwritten chinese word recognition
In this paper, we propose an orientation free method for unconstrained cursive handwritten Chinese word recognition. By a novel gravity center balancing method, the orientation of...
Teng Long, Lianwen Jin
ICDAR
2003
IEEE
13 years 10 months ago
A Study on Top-down Word Image Generation for Handwritten Word Recognition
This paper describes a top-down word image generation model for holistic handwritten word recognition. To generate a word image, it uses likelihoods based, respectively, on a ling...
Eiki Ishidera, Daisuke Nishiwaki