Using Genetic Programming for Character Discrimination in Damaged Documents.
Daniel RiveroJuan R. RabuñalJulian DoradoAlejandro PazosPublished in: EvoWorkshops (2004)
Keyphrases
- information retrieval
- document collections
- printed documents
- document classification
- xml documents
- metadata
- web documents
- text lines
- text documents
- document clustering
- feature selection
- electronic documents
- multi document summarization
- legal documents
- structured documents
- document retrieval
- relevant documents
- document images
- writing style
- retrieved documents
- scanned documents
- ocr systems
- printed characters
- time stamped
- multimedia documents
- optical character recognition
- keywords
- data mining
- missing data
- website