https://github.com/mr-destructive/ocr-playground
https://github.com/mr-destructive/ocr-playground
Last synced: 11 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/mr-destructive/ocr-playground
- Owner: Mr-Destructive
- Created: 2023-09-28T13:41:11.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-09-28T13:53:53.000Z (over 2 years ago)
- Last Synced: 2025-01-29T20:37:18.547Z (over 1 year ago)
- Language: Python
- Size: 8.79 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## OCR Playground
> This is a side project / assigment for understanding and learning OCRs/text extraction.
- Using [tesseract](https://tesseract-ocr.github.io/tessdoc/Installation.html) as the OCR.
- Using [PILLOW](https://pillow.readthedocs.io/en/stable/) for image processing.
- Using [flask](https://flask.palletsprojects.com/en/1.1.x/) for the API.
### Endpoints
- `/uploads`: to upload the image/pdf and get the OCR results.
- `/extract`: get text of rows related to particular column.
- `/rotate`: rotate the image/bounding box in the ocr provided with the angle.
- `/boxes`: get the bounding boxes in the entire document as a image.
### TODO
- Exploration of various concepts like OCRs, IDPs, OCDs, etc.
- Implement the rotation feature more accurately.
- Extract with the entire text resembling the document structure.