Document image improvment for OCR as a classification problem.
Kristen Maria SummersPublished in: DRR (2003)
Keyphrases
- document images
- optical character recognition
- document image analysis
- page segmentation
- document analysis
- printed documents
- document processing
- pattern recognition
- classification accuracy
- scanned documents
- page layout
- ocr systems
- document image retrieval
- character recognition
- text lines
- historical documents
- word level
- language identification
- text classification
- feature extraction
- feature selection
- binarization method
- document image understanding
- scanned images
- feature set
- feature space
- digital libraries
- face recognition
- metadata