Sciweavers

323 search results - page 9 / 65
» A Shared Parts Model for Document Image Recognition
Sort
View
ICDAR
2003
IEEE
14 years 26 days 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
ICDAR
2005
IEEE
14 years 1 months ago
A Corpus for Comparative Evaluation of OCR Software and Postcorrection Techniques
We describe a new corpus collected for comparative evaluation of OCR-software and postcorrection techniques. The corpus is freely available for academic groups and use. The major ...
Stoyan Mihov, Klaus U. Schulz, Christoph Ringlstet...
ICDAR
2009
IEEE
13 years 5 months ago
Learning on the Fly: Font-Free Approaches to Difficult OCR Problems
Despite ubiquitous claims that optical character recognition (OCR) is a "solved problem," many categories of documents continue to break modern OCR software such as docu...
Andrew Kae, Erik G. Learned-Miller
ICDAR
2011
IEEE
12 years 7 months ago
BLSTM Neural Network Based Word Retrieval for Hindi Documents
—Retrieval from Hindi document image collections is a challenging task. This is partly due to the complexity of the script, which has more than 800 unique ligatures. In addition,...
Raman Jain, Volkmar Frinken, C. V. Jawahar, Raghav...
ICDAR
2003
IEEE
14 years 26 days ago
A Line Drawings Degradation Model for Performance Characterization
Line detection algorithms constitute the basis for technical document analysis and recognition. The performance of these algorithms decreases as the quality of the documents degra...
Jian Zhai, Liu Wenyin, Dov Dori, Qing Li