Lost in OCR-Translation: Pixel-based Text Reflow to the Rescue: Magnification of Archival Raster Image Documents in the Browser without Horizontal Scrolling.
Frode Eika SandnesPublished in: PETRA (2022)
Keyphrases
- scanned documents
- printed documents
- scanned images
- text lines
- document processing
- document images
- text documents
- scanned document images
- optical character recognition
- information retrieval
- post processing
- input image
- text information
- document analysis
- image classification
- web documents
- high resolution
- image content
- text recognition
- page layout
- textual information
- image retrieval
- hough transform
- image features
- noise removal
- character recognition
- web images
- electronic documents
- digital libraries
- text retrieval
- text queries
- ocr systems
- user interaction
- information retrieval systems
- semantic information
- textual descriptions
- xml documents
- historical documents
- multimedia documents
- printed text
- metadata