Sciweavers

20 search results - page 3 / 4
» Eliciting Domain Knowledge in Handwritten Digit Recognition
Sort
View
ICDAR
2009
IEEE
13 years 3 months ago
New Trends in Digital Scanning Processes
Handwritten document analysis and recognition deals with several different application fields. In document processing, one of the first problems that must be solved is data acquis...
Sebastiano Impedovo, Raffaele Modugno, Anna Ferran...
ICPR
2000
IEEE
14 years 7 months ago
Experiments with an Extended Tangent Distance
Invariance is an important aspect in image object recognition. We present results obtained with an extended tangent distance incorporated in a kernel density based Bayesian classi...
Daniel Keysers, Hermann Ney, Jörg Dahmen, Tho...
NIPS
1994
13 years 7 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...
ICML
2006
IEEE
14 years 6 months ago
Nightmare at test time: robust learning by feature deletion
When constructing a classifier from labeled data, it is important not to assign too much weight to any single input feature, in order to increase the robustness of the classifier....
Amir Globerson, Sam T. Roweis
EURASIP
1990
13 years 10 months ago
Inversion in Time
Inversionof multilayersynchronous networks is a method which tries to answer questions like What kind of input will give a desired output?" or Is it possible to get a desired...
Sebastian Thrun, Alexander Linden