Adaptive detection of missed text areas in OCR outputs: application to the automatic assessment of OCR quality in mass digitization projects.
Ahmed Ben SalahNicolas RagotThierry PaquetPublished in: DRR (2013)
Keyphrases
- text recognition
- automatic assessment
- optical character recognition
- printed documents
- text lines
- post processing
- ocr systems
- character recognition
- text extraction
- document images
- preprocessing
- document processing
- text localization and recognition
- page layout
- scanned documents
- error correction
- digital mammography
- recognition errors
- case study
- printed text
- information retrieval
- handwriting recognition
- document analysis
- learning strategies