Japanese OCR Error Correction using Character Shape Similarity and Statistical Language Model.
Masaaki NagataPublished in: COLING-ACL (1998)
Keyphrases
- error correction
- language model
- shape similarity
- shape descriptors
- n gram
- shape matching
- information retrieval
- shape representation
- probabilistic model
- retrieval model
- optical character recognition
- test collection
- query expansion
- mixture model
- distance function
- dynamic time warping
- similarity metrics
- matching scheme
- shape features
- similarity metric
- spatial relationships
- distance measure
- d objects
- cortical surface
- shape analysis
- statistical models