Word level script recognition for Uighur document mixed with English script.
Hao YeLiangrui PengPublished in: MOCR@ICDAR (2013)
Keyphrases
- word level
- document analysis
- document images
- language identification
- machine translation
- language independent
- english text
- word recognition
- character recognition
- n gram
- image analysis
- word segmentation
- sentence pairs
- sentence level
- word spotting
- source language
- text lines
- viterbi algorithm
- semantic roles
- natural language
- information retrieval
- text analysis