Script-agnostic text reflow for document images
- Resource Type
- Patent
- Authors
- Source
- Subject
- Language
Script-agnostic text reflow technique embodiments are presented that generally reflow text found in an image of a document in a manner that functions across multiple scripts, multiple fonts of a script and multiple languages using the same script. This generally involves segmenting regions of text in a document image into individual words and doing this without relying on any script-specific characteristics or requiring any form of character recognition. While segmenting text, the possible presence of accents, diacritics and punctuation marks is considered.