Textual Information Extraction in Document Images Guided by a Concept Lattice.
Cynthia PitouJean DiattaPublished in: CLA (2016)
Keyphrases
- document images
- concept lattice
- information extraction
- textual data
- formal concept analysis
- document image analysis
- natural language
- document analysis
- natural language processing
- formal concepts
- formal contexts
- text mining
- rough sets
- rough set theory
- knowledge discovery
- association rule mining
- classification rules
- text processing
- information retrieval
- machine learning
- document image retrieval
- page segmentation
- scanned documents
- association rules
- scanned document images
- optical character recognition
- pattern recognition
- multiscale
- textual information
- historical documents
- page layout
- printed text
- real world
- high dimensional
- printed documents
- decision trees
- support vector machine
- word spotting
- nearest neighbor
- genetic programming