Abstract
Printed pages can be linked to videos, explanations, translations, and interactive controls without adding a visible code or marker to the page. The system described here identifies a page from its own words and layout, looks up digital attachment points stored as fractions of the page width and height, and projects those points into a live camera image. Because the attachment points are independent of pixels, they remain aligned when the page is printed at a different size, rotated, or viewed at an angle. A staged recognition process first uses recognized text, then page layout, and finally the overall visual appearance when text cannot be read reliably. This article specifies the records, processing steps, coordinate calculations, operating thresholds, and validation procedure needed to build a working prototype on a phone, tablet, laptop, or similar camera-equipped device.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "Invisible Anchor Document Augmentation", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/11828