Digitizing a Million Books: Challenges for Document Analysis.
K. Pramod SankarVamshi AmbatiLakshmi PrathaC. V. JawaharPublished in: Document Analysis Systems (2006)
Keyphrases
- document analysis
- document images
- document image analysis
- character recognition
- image analysis
- printed documents
- real world
- document processing
- text analysis
- document image retrieval
- information retrieval
- word recognition
- feature selection
- artificial intelligence
- k nearest neighbor
- language model
- multimedia
- word level
- neural network
- electronic documents
- databases