N-gram language models for document image decoding.
Gary E. KopecMaya R. SaidKris PopatPublished in: Document Recognition and Retrieval (2002)
Keyphrases
- document images
- document image analysis
- n gram
- document analysis
- document image understanding
- optical character recognition
- document processing
- language independent
- scanned document images
- text lines
- viterbi algorithm
- language identification
- scanned documents
- word level
- image processing
- handwritten documents
- printed documents
- page layout
- binarization method
- printed text
- document layout
- gray scale
- image segmentation