Skip to content

python ocr using tesseract/ with EAST opencv detector

License

Notifications You must be signed in to change notification settings

danwald/pytextractor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

83 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pytextractor

python ocr using tesseract with EAST opencv text detector

Uses the EAST opencv detector with pytesseract to extract text(default) or numbers from images.

Usage main

usage: text_detector [-h] [--east EAST] [-c CONFIDENCE] [-w WIDTH] [-e HEIGHT] [-d] [-n] [-p PERCENTAGE]
                     [-b MIN_BOXES] [-i MAX_ITERATIONS]
                     images [images ...]

Text/Number extractor from image

positional arguments:
  images                path(s) to input image(s)

options:
  -h, --help            show this help message and exit
  --east EAST           path to input EAST text detector
  -c CONFIDENCE, --confidence CONFIDENCE
                        minimum probability required to inspect a region
  -w WIDTH, --width WIDTH
                        resized image width (should be multiple of 32)
  -e HEIGHT, --height HEIGHT
                        resized image height (should be multiple of 32)
  -d, --display         Display bounding boxes
  -n, --numbers         Detect only numbers
  -p PERCENTAGE, --percentage PERCENTAGE
                        Expand/shrink detected bound box
  -b MIN_BOXES, --min-boxes MIN_BOXES
                        minimum number of detected boxes to return
  -i MAX_ITERATIONS, --max-iterations MAX_ITERATIONS

Installation & usage

brew install tesseract
pipx install pytextractor
text_detector

Usage lib

from pytextractor import pytextractor

extractor = pytextractor.PyTextractor()

Running tests

brew install tesseract
python -mvenv .venv --prompt .
. ./.venv/bin/activate
pip install ".[dev]"
pytest -s tests

About

python ocr using tesseract/ with EAST opencv detector

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages