caa a22 4500 445379545 CHVBK 20180317143013.0 cr unu---uuuuu 170323e20110901xx s 000 0 eng 10.1007/s10032-011-0164-6 doi (NATIONALLICENCE)springer-10.1007/s10032-011-0164-6 Learning on the fly: a font-free approach toward multilingual OCR [Elektronische Daten] [Andrew Kae, David Smith, Erik Learned-Miller] Despite ubiquitous claims that optical character recognition (OCR) is a "solved problem,” many categories of documents continue to break modern OCR software such as documents with moderate degradation or unusual fonts. Many approaches rely on pre-computed or stored character models, but these are vulnerable to cases when the font of a particular document was not part of the training set or when there is so much noise in a document that the font model becomes weak. To address these difficult cases, we present a form of iterative contextual modeling that learns character models directly from the document it is trying to recognize. We use these learned models both to segment the characters and to recognize them in an incremental, iterative process. We present results comparable with those of a commercial OCR system on a subset of characters from a difficult test document in both English and Greek. Springer-Verlag, 2011 Character recognition nationallicence OCR nationallicence Cryptogram nationallicence Font-free models nationallicence Multilingual OCR nationallicence Kae Andrew Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut Smith David Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut Learned-Miller Erik Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut International Journal on Document Analysis and Recognition (IJDAR) Springer-Verlag 14/3(2011-09-01), 289-301 1433-2833 14:3<289 2011 14 10032 https://doi.org/10.1007/s10032-011-0164-6 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10032-011-0164-6 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Kae Andrew Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut NATIONALLICENCE 700 1- Smith David Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut NATIONALLICENCE 700 1- Learned-Miller Erik Department of Computer Science, University of Massachusetts Amherst, 140 Governors Drive, 01003-9264, Amherst, MA, USA aut NATIONALLICENCE 773 0- International Journal on Document Analysis and Recognition (IJDAR) Springer-Verlag 14/3(2011-09-01), 289-301 1433-2833 14:3<289 2011 14 10032 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer