Title :
Teaching a computer to read
Author_Institution :
Rensselaer Polytech. Inst., Troy, NY, USA
fDate :
30 Aug-3 Sep 1992
Abstract :
Current OCR devices generate too many errors due to missegmentation and multifont confusion. Some of these errors can be avoided or corrected though greater use of linguistic context and local shape consistency in printed matter. To teach machines to read, OCR designers should allow their devices to modify their internal parameters according to information gained through a family of internal feedback loops
Keywords :
computational linguistics; document image processing; learning systems; optical character recognition; OCR; linguistic context; local shape consistency; machine learning; optical character recognition; Character recognition; Computer errors; Education; Error correction; Feedback loop; Humans; Optical character recognition software; Optical design; Optical devices; Shape;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201760
