sOCRates - a post-OCR text correction method.
Danny Suarez VargasLucas Lima de OliveiraViviane P. MoreiraGuilherme Torresan BazzoGustavo Acauan LorentzPublished in: SBBD (2021)
Keyphrases
- printed documents
- document processing
- text recognition
- optical character recognition
- page layout
- document images
- ocr systems
- text extraction
- document analysis
- text retrieval
- information retrieval
- keywords
- character recognition
- free text
- text analysis
- scanned documents
- text processing
- automatically extracted
- post processing
- preprocessing
- database
- data mining
- text mining
- digital libraries
- error correction
- scanned images
- multimedia