Combination of Optical Character Recognition Engines for Documents Containing Sparse Text and Alphanumeric Codes.
Iago Lourenço CorreaPaulo Lilles Jorge Drews JuniorRicardo Nagel RodriguesPublished in: SIBGRAPI (2021)
Keyphrases
- optical character recognition
- ocr systems
- printed documents
- document images
- printed text
- text lines
- text recognition
- character recognition
- scanned documents
- word spotting
- historical manuscripts
- character segmentation
- character n grams
- handwriting recognition
- text extraction
- document processing
- document analysis
- page segmentation
- text documents
- image binarization
- document image analysis
- text regions
- information retrieval systems
- image processing
- information retrieval
- text segmentation
- handwritten documents
- real time
- language independent
- machine vision
- text retrieval
- language model
- handwritten text
- hidden markov models