Omnifont and Unlimited-Vocabulary OCR for English and Arabic.
Issam BazziChristopher LaPreJohn MakhoulChristopher RaphaelRichard M. SchwartzPublished in: ICDAR (1997)
Keyphrases
- optical character recognition
- language identification
- arabic language
- document images
- english text
- printed documents
- arabic documents
- ocr systems
- vocabulary learning
- text recognition
- isolated word
- character recognition
- natural language
- english language
- language learning
- speech recognition
- machine translation
- unknown words
- handwriting recognition
- character n grams
- english vocabulary
- post processing
- word forms
- document processing
- preprocessing
- answer questions
- spoken language
- scanned documents
- handwritten documents
- word level
- computer assisted language learning
- statistical machine translation
- printed text
- cross lingual
- parallel processing
- natural language processing
- digital libraries