https://github.com/robmarkcole/text-insights-app

Upload an image of a document and extract text, names, facts and figures
https://github.com/robmarkcole/text-insights-app

streamlit tesseract-ocr

Last synced: about 1 month ago
JSON representation

Upload an image of a document and extract text, names, facts and figures

• Host: GitHub
• URL: https://github.com/robmarkcole/text-insights-app
• Owner: robmarkcole
• License: apache-2.0
• Created: 2020-05-27T02:37:50.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2024-08-12T20:16:21.000Z (6 months ago)
• Last Synced: 2024-12-24T20:02:01.764Z (about 1 month ago)
• Topics: streamlit, tesseract-ocr
• Language: Python
• Size: 331 KB
• Stars: 22
• Watchers: 2
• Forks: 9
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# text-insights-app

Upload an image of a document and extract text, names, facts and figures. Use tesseract for OCR.

* First follow the readme in `tesseract-engine` then follow the readme in `streamlit-ui`

* todo: add docker-compose up







## References

* https://github.com/patidarparas13/Sentiment-Analyzer-Tool

* [Radiological report analytics](https://twitter.com/beringresearch/status/1257623872465240064)

* [twitter sentiment](https://twitter.com/zachrenwick/status/1258664133764890624)

* [Summarization using bert model (pytorch)](https://github.com/holladileep/TextSummarizationPipeline-AWS)

* [Named entity example](https://maelfabien.github.io/project/Streamlit/#dockerfile)