https://github.com/yuvix25/pydocscanner
Scan documents with python
https://github.com/yuvix25/pydocscanner
document-scanner ocr python super-resolution
Last synced: 3 months ago
JSON representation
Scan documents with python
- Host: GitHub
- URL: https://github.com/yuvix25/pydocscanner
- Owner: Yuvix25
- License: gpl-3.0
- Created: 2020-11-12T07:37:20.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2020-11-12T11:24:44.000Z (over 4 years ago)
- Last Synced: 2025-01-19T10:09:54.430Z (4 months ago)
- Topics: document-scanner, ocr, python, super-resolution
- Language: Python
- Homepage:
- Size: 33 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# PyDocScanner
## Requirements
- Python 3 (tested on Python 3.8)
- tesseract
- opencv-python built with gpu (if you won't use super resolution regular opencv-python will do it)
## Installation
Install with Git:
```sh
$ git clone https://github.com/Yuvix25/PyDocScanner.git
$ cd PyDocScanner
$ python setup.py install
```
Install with pip - Coming Soon
# Usage
```python
# imports
from PyDocScanner import Scan
import cv2
# read image from file:
image = cv2.imread("path_to_file")
# scan the document with all features (color filter, super resolution, and ocr):
document_image, text = Scan(image, apply_color_filter=True, do_super_reso=True, do_ocr=True)
# scan the document without ocr:
document_image = Scan(image, apply_color_filter=True, do_super_reso=True, do_ocr=False)
```