10500 search results - page 361 / 2100 » Documentation for |
186
click to vote
ICDAR
2009
IEEE
16 years 2 months ago
2009
IEEE
In document image understanding, public datasets with ground-truth are an important part of scientific work. They are not only helpful for developing new methods, but also provid...
185
click to vote
FQAS
2009
Springer
16 years 2 months ago
2009
Springer
The bag of words representation (BoW), which is widely used in information retrieval (IR), represents documents and queries as word lists that do not express anything about context...
173
click to vote
ICPR
2008
IEEE
16 years 2 months ago
2008
IEEE
In order to preserve our cultural heritage and for automated document processing libraries and national archives have started digitizing historical documents. In the case of degra...
165
click to vote
ICPR
2008
IEEE
16 years 2 months ago
2008
IEEE
A crucial preprocessing stage in applications such as OCR is text extraction from mixed-type documents. The present work, in contrast to most until now, successfully faces the pro...
213
click to vote
ICDAR
2007
IEEE
16 years 1 months ago
2007
IEEE
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...