The Multistage Approach to Information Extraction in Degraded Document Images.
Yan ChenGraham LeedhamPublished in: ICPR (1) (2004)
Keyphrases
- multistage
- document images
- information extraction
- ocr systems
- production system
- natural language processing
- document analysis
- document image analysis
- stochastic programming
- optical character recognition
- single stage
- text mining
- dynamic programming
- lot sizing
- document image understanding
- information retrieval
- document processing
- machine learning
- question answering
- printed documents
- text analysis
- scanned documents
- page segmentation
- historical documents
- scanned document images
- machine translation
- text documents
- interconnection networks
- language identification
- text processing
- text classification
- page layout
- document image retrieval
- digital libraries
- natural language