A packaged OCR model to read texts into WoW screenshots
Project description
WoW Screenshot OCR
Deep learning OCR models to read text from WoW screenshots. Based on a detector that spots text frames, and a recognizer that reads text from detected frames.
- Chat
- Combat log
- Nameplates
- UI frames
- Map
Installation
pip install wow-ocr
Usage
Models use pre trained weights, you don't have to train anything. Try it on Colab
import wow_ocr
# Init pipeline, detector and recognizer models with pre trained weights
pipeline = wow_ocr.pipeline.Pipeline()
# Screenshots example
images = [
wow_ocr.tools.read(url)
for url in [
"https://image_url.com/1.jpg",
"https://image_url.com/2.jpg",
]
]
# Results - Image to Text
prediction_groups = pipeline.recognize(images)
# # Each list of predictions in prediction_groups is a list of
# # (word, box) tuples.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
wow-ocr-0.0.3.tar.gz
(21.2 kB
view hashes)
Built Distribution
wow_ocr-0.0.3-py3-none-any.whl
(22.1 kB
view hashes)