Metadata-Version: 2.1
Name: video-ocr
Version: 0.0.1
Summary: Package to run OCR on videos
Author: Veneet Reddy
License: UNKNOWN
Project-URL: Documentation, https://github.com/PinkFloyded/video-ocr
Project-URL: Source, https://github.com/PinkFloyded/video-ocr
Project-URL: Tracker, https://github.com/PinkFloyded/video-ocr/issues
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: End Users/Desktop
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Image Processing
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Provides-Extra: dev
License-File: LICENSE

# video-ocr

video-ocr is a command line tool and a python library that performs OCR on video frames, reducing the computational effort by choosing only frames that are different from their adjacent frames.


## Installation

1. video-ocr uses [tesserocr](https://github.com/sirfz/tesserocr), which in turn uses [tesseract](https://github.com/tesseract-ocr/tesseract) as the OCR engine. So, please follow the tesserocr installation instructions.
2. Install using pip: `pip install video-ocr`

## Getting started
### Command line usage
Run `video-ocr --help` to show the help text. Example usage is
```bash
video-ocr /path/to/video.mp4 --sample_rate=1 --debug_dir="path/to/debug/dir"
```
### Python usage
```python
import video_ocr
video_ocr.perform_video_ocr("/Users/veneetreddy/Downloads/texts.mp4", sample_rate=1)
```



