github

matthewearl / deep-anpr

  • вторник, 10 мая 2016 г. в 03:12:58
https://github.com/matthewearl/deep-anpr

Python
Using neural networks to build an automatic number plate recognition system



Deep ANPR

Using neural networks to build an automatic number plate recognition system. See this blog post for an explanation.

Usage is as follows:

  1. ./extractbgs.py SUN397.tar.gz: Extract ~3GB of background images from the SUN database into bgs/. (bgs/ must not already exist.) The tar file (36GB) can be downloaded here. This step may take a while as it will extract 108,634 images.

  2. ./gen.py 1000: Generate 1000 test set images in test/. (test/ must not already exist.) This step requires UKNumberPlate.ttf to be in the current directory, which can be downloaded here.

  3. ./train.py: Train the model. A GPU is recommended for this step.

  4. ./detect.py in.jpg weights.npz out.jpg: Detect number plates in an image.

The project has the following dependencies: