December 2024

AI Camera

The StealthCam project was born out of a desire to explore the possibilities offered by the Internet of Things (IoT) by creating a smart home security system for our connected object course at Cégep de Rosemont. The idea was to merge hardware (sensors and cameras) with modern software technologies such as facial recognition and artificial intelligence. This project allowed me to learn how to manage communication between sensors, a Python backend processing real-time data streams, and a fluid desktop user interface.

Contribution

On this project, I was responsible for developing the entire architecture, from the backend to the user interface. I set up the Flask server to orchestrate the various services, including managing an SQLite database for activity history. I integrated facial recognition with the face_recognition library and the OpenAI API to generate intelligent textual descriptions of the captured images. On the client side, I developed the desktop application with Electron, using GSAP to create a modern and dynamic interface. I also took care of the configuration of the ultrasonic and sound sensors.

Project Gallery

Visual Overview

Approach

I adopted a modular approach to separate the hardware detection logic from the application layer. The backend functions as a service center where each sensor (motion, sound, light) is processed independently before being synthesized by the server. For the user experience, I chose Electron to provide a robust desktop application capable of communicating easily with the local file system and the Flask server. This structure allows for high system responsiveness, which is crucial for a real-time monitoring device.

Features

Built-in facial recognition
Motion detection Sound
Automatic night mode
AI image description
Automatic video recording
Electron desktop application
Activity history

More Projects

Explore Other Work

Genies

I developed Genies at a pivotal moment when artificial intelligence was beginning to take off in a big way. At that time, powerful tools were scattered across multiple websites, which made the user experience tedious. My goal was to create a single platform capable of centralizing the best AI models to offer simplified access and a consistent interface, allowing users to switch from text generation to visual creation without changing ecosystems.

June 2024

ArtSync

As part of my Web Application 2 course in college, I had the opportunity to work in a team on the design and on the development of a full-stack application. We created ArtSync, a platform where users can publish, explore, and share artistic content. The project took us through all stages of development: requirements analysis, UML diagram, relational database design, interface design with Figma, and development using Java, Spring Boot, Thymeleaf, and Angular. It was a great experience to put our knowledge into practice in an agile environment, with regular follow-ups and a workflow that felt very close to a real professional project.

May 2024

Genie Optiroll

As a piano player, I often find reading traditional sheet music time-consuming and prefer visual piano rolls. Since not every song has a piano roll tutorial available online, I wanted to build a tool that could instantly convert any sheet music into an interactive piano roll. Adding built-in speed controls allows me to slow down complex sections, making it much easier to learn new music directly at my piano. Additionally, for quite a while, I wanted to revisit my original "Genies" project from 2024 to build a "v2". I decided to start a new series of standalone applications under the "Genie" brand, where all my AI and computer vision projects will be categorized. That is why the project name starts with "Genie:", while "Optiroll" is a blend of "Optical" (from Optical Music Recognition) and "Roll" (from Piano Roll).

March 2026

View All Projects