Re:Ask HN: What are you working on? (April 2025)
by perihelions on Monday April 28, 2025 @04:23AM
(#43818906)
You're inferring the structure of the document from the printed result. If typesetting takes a set of layout directives and outputs a page, this is taking a finished page and guessing what layout directives could create it. Then you can take that inferred structure and reflow the page in a new layout.
[ Parent
| on HN ]
Re:Ask HN: What are you working on? (April 2025)
by froh on Monday April 28, 2025 @04:39AM
(#43819000)
so like ocr but not recognizing characters and words but recognizing the layouted structure and transforming it into content markup and layout markup?
Re:Ask HN: What are you working on? (April 2025)
by perihelions on Monday April 28, 2025 @04:47AM
(#43819039)
That's a way to view it!
The reason I'm not falling back on OCR is because the general case is full of things, like math equations and inset graphics/diagrams, that can't be OCR'd. The only robust way to deal with those is to treat them as graphical atoms: "this bounding box can be moved around, but should not be split up into pieces".