sovse/tflite_avto_num_recognation

License plate recognition . Model training and conversion to tflite

33
/ 100
Emerging

Implements a complete pipeline combining object detection (ResNet50-based plate localization), geometric alignment, and character-level OCR using TensorFlow 2/Keras for training with TensorFlow Lite inference optimization. Targets Russian license plate formats through a multi-stage approach: detecting and cropping plates, aligning skewed images, then recognizing individual characters. Designed for deployment on edge devices (embedded controllers, mobile phones) via TFLite quantized models.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

42

Forks

10

Language

Jupyter Notebook

License

Last pushed

Mar 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sovse/tflite_avto_num_recognation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.