Skip to main content

AI-Powered System for Detecting License Plates of Vehicles in Infraction

AI-Powered System for Detecting License Plates of Vehicles in Infraction

The AI License plate violation detector (Whistleblower) dApp is a revolutionary application leveraging chain-verifiable image recognition powered by AI algorithms. Spearheaded by Think and Dev, a leading technology company specializing in blockchain and AI development, the project is part of Cartesi's grants program and focuses on revolutionizing real-time traffic violation detection through decentralized application (dApp) implementation.
Proof of conceptAI/ML


María Mercedes Vazzano
Juan Manuel Aragón Paz
Lucas Marc

Share project


"Whistleblower" seeks to construct an on-chain verifiable image recognition system utilizing AI algorithms seamlessly operating within the Cartesi virtual machine. The primary objective is to identify license plates of vehicles violating traffic laws, with the identified information securely stored on the blockchain to provide indisputable evidence of the infringement.

To encourage community engagement and knowledge sharing, we provide comprehensive project documentation, open-source code, and pre-built wheels. Leveraging Cartesi's capabilities, our aim is to address real-world challenges with cutting-edge technology, ensuring accessibility and usability through pre-built wheels for easy software installation within the community.

Our proof of concept (PoC) demonstrates the AI-based traffic violation recognition system's capabilities within the Cartesi Machine. The PoC showcases Cartesi's efficacy in executing a trained model utilizing the YOLO object detection algorithm and character recognition systems, enabling real-time license plate identification while excluding the resource-intensive model training phase.

Additionally, we have developed a user-friendly interface seamlessly integrating image input into the Cartesi Machine. This interface streamlines the process of processing and storing images, along with their associated license plate numbers, on the blockchain. Users can effortlessly access this information through a simple GraphQL query to the list of alerts generated by our DApp, exemplifying Cartesi's role in enhancing data accessibility and management.

Our commitment to transparent documentation empowers developers and enthusiasts within the Cartesi community. By openly sharing our findings and experiences, we aim to foster discussions and knowledge-sharing, highlighting Cartesi's potential for diverse applications beyond traffic violation recognition.

What's next

Looking ahead, our project roadmap includes key steps to further improve the functionality and efficiency of our system:

  • Improving character detection algorithms.
  • Notification of violations to competent authorities and violators.
  • Integration of smart contracts to manage fine payments and ensure a transparent record of transactions in the chain.
  • Implementation of an interactive dispute resolution system to address outcome disputes.

Through these future developments, we intend to create a comprehensive and efficient solution for the detection and management of traffic violations, taking full advantage of Cartesi's innovative technology stack.


Last updated: Mar 27, 2024
Anyone is free to submit information about their project. Do your own research and use your best judgment when using or interacting with any of the projects listed in this directory. Being listed in this directory is not an endorsement from the Cartesi Foundation or any other related entity.

Explore similar projects

Hackathon Project


Blockchain marketplace where people get paid for helping train ML models and don’t need to share their data with anyone.

Last updated: Oct 20, 2023
Iris Classifier
Proof of concept

Iris Classifier

On-Chain KNN Flower Prediction

Last updated: Nov 2, 2023
Teach AI
Hackathon Project

Teach AI

The application helps to curate high-quality datasets by providing a framework to incentivize RLHF, with the LLM being fully verifiable and hosted on-chain.

Last updated: Oct 20, 2023