Abstract
Enhancing a mobile scanned document is a very difficult task that the majority of state-of-the-art solutions
fail. This is addressed mainly because the algorithms cannot correctly distinguish the document’s content
from the background. To overcome this issue, this work proposes a workflow that uses a sequence of
machine learning models to address content segmentation, background removal, and content
enhancement.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "A WORKFLOW FOR DOCUMENT ENHANCEMENT THROUGH CONTENT SEGMENTATION AND MULTIPLE ENHANCEMENTS", Technical Disclosure Commons, (April 10, 2020)
https://www.tdcommons.org/dpubs_series/3119