Detecting and extracting image document components to create flow document
US9355313B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 11, 2014 |
| Grant date | May 31, 2016 |
| Priority date | — |
| Expiry date | Jul 30, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/416
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
One or more components of an image document may be detected and extracted in order to create a flow document from the image document. Components of an image document may include text, one or more paths, and one or more images. The text may be detected using optical character recognition (OCR) and the image document may be binarized. The detected text may be extracted from the binarized image document to enable detection of the paths, which may then be extracted from the binarized image document to enable detection of the images. In some examples, the images, similar to the text and paths, may be extracted from the binarized image document. The extracted text, paths, and/or images may be stored in a data store, and may be retrieved in order to create a flow document that may provide better adaption to a variety of reading experiences and provide editable documents.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.