Digitalisierung historischer Zeitungen aus dem Blickwinkel der automatisierten Text- und Strukturerkennung (OCR).
Günter MühlbergerPublished in: ZfBB (2011)
Keyphrases
- text recognition
- document processing
- printed documents
- text extraction
- page layout
- optical character recognition
- text retrieval
- database
- document analysis
- post processing
- character recognition
- scanned documents
- document images
- information retrieval
- ocr systems
- text mining
- text documents
- digital libraries
- keywords
- free text
- viterbi algorithm
- preprocessing
- text lines
- scanned images