[
https://issues.apache.org/jira/browse/TIKA-2092?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Craig Pfeifer updated TIKA-2092:
--------------------------------
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.
was:
"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
Would be useful as part of the OCR efforts in tika.
> Integrate Math equation image extraction
> ----------------------------------------
>
> Key: TIKA-2092
> URL: https://issues.apache.org/jira/browse/TIKA-2092
> Project: Tika
> Issue Type: Improvement
> Components: detector, ocr
> Affects Versions: 2.0
> Reporter: Craig Pfeifer
> Labels: deeplearning, image, parse
>
> "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.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
