Sciweavers

216 search results - page 31 / 44
» Handwritten Character Recognition Based on Structural Charac...
Sort
View
DAS
2010
Springer
15 years 1 months ago
Improved classification through runoff elections
We consider the problem of dealing with irrelevant votes when a multi-case classifier is built from an ensemble of binary classifiers. We show how run-off elections can be used to...
Oleg Golubitsky, Stephen M. Watt
ICDAR
2009
IEEE
14 years 7 months ago
Recurrent HMMs and Cursive Handwriting Recognition Graphs
Standard cursive handwriting recognition is based on a language model, mostly a lexicon of possible word hypotheses or character n-grams. The result is a list of word alternatives...
Marc-Peter Schambach
ICASSP
2011
IEEE
14 years 1 months ago
Maximum margin structure learning of Bayesian network classifiers
Recently, the margin criterion has been successfully used for parameter optimization in graphical models. We introduce maximum margin based structure learning for Bayesian network...
Franz Pernkop, Michael Wohlmay, Manfred Mücke
NIPS
1994
14 years 11 months ago
Using a neural net to instantiate a deformable model
Deformable models are an attractive approach to recognizing nonrigid objects which have considerable within class variability. However, there are severe search problems associated...
Christopher K. I. Williams, Michael Revow, Geoffre...
ECAI
2008
Springer
14 years 11 months ago
Sequential spatial reasoning in images based on pre-attention mechanisms and fuzzy attribute graphs
Spatial relations play a crucial role in model-based image recognition and interpretation due to their stability compared to many other image appearance characteristics, and graphs...
Geoffroy Fouquier, Jamal Atif, Isabelle Bloch