[TIKA-2092] Integrate Math equation image extraction

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Affects Version/s: 2.0.0
• Component/s: detector, ocr
• Labels: deeplearning image parse
• Assignee: Unassigned
• Reporter: Craig Pfeifer
• Created: 22/Sep/16 17:12
• Updated: 12/Apr/21 13:00

Description

"A general-purpose, deep learning-based system to decompile an image into presentational markup."

As described in :

What You Get Is What You See: A Visual Markup Decompiler
Yuntian Deng, Anssi Kanervisto, and Alexander M. Rush
http://arxiv.org/pdf/1609.04938v1.pdf

code here:
https://github.com/harvardnlp/im2markup

demo here:
http://lstm.seas.harvard.edu/latex/

Would be useful as part of the OCR efforts in tika.