An Omnifont Open-Vocabulary OCR System for English and Arabic.

Issam Bazzi Richard M. Schwartz John Makhoul

Published in: IEEE Trans. Pattern Anal. Mach. Intell. (1999)

Keyphrases

optical character recognition
language identification
arabic language
document images
arabic documents
ocr systems
english text
printed documents

character recognition
handwriting recognition
natural language
vocabulary learning
text recognition
language learning
post processing
preprocessing

isolated word
machine translation
speech recognition
english vocabulary
word spotting
word forms
error correction
cross lingual

arabic handwriting recognition
character n grams
unknown words
reading comprehension
statistical machine translation
query translation
cross language information retrieval
cross language