Extraction of character strings from unformed document images.
Kei TakizawaDaisaku AritaMichihiko MinohKatsuo IkedaPublished in: ICDAR (1993)
Keyphrases
- document images
- optical character recognition
- ocr systems
- printed documents
- machine printed
- line extraction
- text lines
- document image analysis
- document analysis
- printed text
- document image understanding
- page layout
- scanned documents
- word spotting
- information extraction
- historical documents
- text extraction
- language identification
- document image retrieval
- image binarization
- document layout
- image processing
- scanned document images
- page segmentation
- document processing
- handwritten documents
- word level
- binarization method
- scanned images
- edit distance
- text classification