Sciweavers

1098 search results - page 42 / 220
» Visual Word Ambiguity
Sort
View
ICDAR
2009
IEEE
14 years 11 months ago
Italic or Roman: Word Style Recognition without A Priori Knowledge for Old Printed Documents
This paper presents an Italic/Roman word type recognition system without a priori knowledge on the characters' font. This method aims at analyzing old documents in which char...
Loris Eynard, Hubert Emptoz
112
Voted
3DPVT
2006
IEEE
202views Visualization» more  3DPVT 2006»
15 years 8 months ago
Visual Shapes of Silhouette Sets
Shape from silhouette methods are extensively used to model dynamic and non-rigid objects using binary foreground-background images. Since the problem of reconstructing shapes fro...
Jean-Sébastien Franco, Marc Lapierre, Edmon...
ICPR
2002
IEEE
15 years 6 months ago
Progress in Document Reconstruction
We combine information from a language model and character image pattern matching to iteratively reduce ambiguity in document images. Combining word shape information and lists of...
A. Lawrence Spitz
ACL
1998
15 years 3 months ago
Learning Constraint Grammar-style Disambiguation Rules using Inductive Logic Programming
This paper reports a pilot study, in which Constraint Grammar inspiredruleswere learnt using the Progol machine-learning system. Rules discarding faulty readings of ambiguously ta...
Nikolaj Lindberg, Martin Eineborg
MP
2006
106views more  MP 2006»
15 years 1 months ago
Worst-case distribution analysis of stochastic programs
We show that for even quasi-concave objective functions the worst-case distribution, with respect to a family of unimodal distributions, of a stochastic programming problem is a u...
Alexander Shapiro