https://github.com/pabsan-0/latency-ocr
Scripts to test video latency using tesseract for timestamp OCR
https://github.com/pabsan-0/latency-ocr
ocr opencv repos-devtools tesseract
Last synced: 15 days ago
JSON representation
Scripts to test video latency using tesseract for timestamp OCR
- Host: GitHub
- URL: https://github.com/pabsan-0/latency-ocr
- Owner: pabsan-0
- Created: 2024-02-05T14:02:51.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-02-06T11:58:52.000Z (over 2 years ago)
- Last Synced: 2025-01-23T16:53:03.503Z (over 1 year ago)
- Topics: ocr, opencv, repos-devtools, tesseract
- Language: Python
- Homepage:
- Size: 522 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Latency profiler
## Dependencies
- Python packages: OpenCV, Pillow, Pytesseract. `pip3 install -r requirements.txt`
- Tesseract executable: `apt install tesseract-ocr`
## Usage
Here's the detailed walkthrough:
- Run `./clocks.sh` on a terminal and zoom in for bigger characters.
- Start your video pipeline and point the camera to the `./clocks.sh` terminal.
- Have your video show its output on your screen.
- Run `./main.py` and use your left and middle mouse buttons to enclose the clocks.
- Press `q` to continue.
- The time difference in between clocks should be printing on your screen.
For more, call `main.py --help`. Expect having to do some image fine-tuning
(thresholding, grayscaling...), mostly due to Tesseract's pitfalls.
