An Omnifont Open-Vocabulary OCR System for English and Arabic.
Issam BazziRichard M. SchwartzJohn MakhoulPublished 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