Diginix - Ai booked orders value 180,000 USD in the month of December

Car properties and damage recognition for an insurance company

AboutThe Client

The project was implemented for one of the largest insurance companies in Georgia. The final goal of the project was automatization of car damage estimation and integration API with the company’s mobile app so customers can insure their cars. 

Car insurance
Car insurance (1)
Car insurance (2)

About this project

Project Description

We have developed a neural network to recognize the exact damaged area of the car from the uploaded image. We have labeled 50 000 car images that made it possible to detect: flat tires, broken windows, dent, vandalism, and crashes. Also, our machine learning model can recognize a brand of the car and determine from which angle the picture was taken. Our client used the model to create a mobile app, enabling users to insure their cars without the involvement of an insurance agent. 


  • PyTorch based convolutional neural networks (Mask-R CNN) + scikit-learn / XGBoost for car properties and damage detection and price estimation.
  • Scrapy for collecting data.

Let's Talk Business

Reach out to us by below-given details, or drop us a text to start a conversation, we are here to provide best in class business solutions.