License plate cover on car images

#python #deeplearning #keras #serverless

Introduction

Goal of this project was to develop and train a Deep learning model capable of detecting and covering license plates of vehicles.

Technical

This project was implemented with Python using the Keras framework on top of Tensorflow.
A number of python libraries like OpenCV, Numpy, Pandas, etc… were used.

Examples

Deployment

A lot of work done in order the reduce the overall size of the code and model weights to allow a deployment in Serverless environments like AWS Lambda and Google Cloud Functions.

Finally i was able to deploy on Google Cloud Function with an API in front.

The serverless approach is very optimal as the scalability is handled for you and serverless is almost always cheap.
In my case, i had a deep learning model that was almost totally free (1 million operations per month for free).

Source:
https://www.ibragim.fr/portfolio/cache-plaque-deep-learning/