Extracting person names from diverse and noisy OCR text.
Thomas L. PackerJoshua F. LutesAaron P. StewartDavid W. EmbleyEric K. RinggerKevin D. SeppiLee S. JensenPublished in: AND (2010)
Keyphrases
- person names
- text extraction
- text recognition
- optical character recognition
- printed documents
- document processing
- automatically extracted
- ocr systems
- named entities
- document analysis
- document images
- printed text
- information retrieval
- post processing
- text mining
- keywords
- text retrieval
- automatically extracting
- character recognition
- text documents
- real world
- page layout
- preprocessing
- scanned documents
- free text
- text information
- noisy data
- complex background
- error correction