Inspiration
What it does
How we built itInspiration
We were inspired by the growing need for faster, more accessible facial verification in both everyday scenarios and high-stakes environments like security and forensics. Current systems often involve long wait times, complicated processes, or inaccessible technology. We wanted to build a tool that could bridge that gap—something efficient, accurate, and easy to use.
What it does
Detectify is a lightweight but powerful facial analysis tool that identifies and highlights differences between faces. Whether it’s for verifying identity in queues or supporting forensic investigations, Detectify makes facial comparison easier and faster by marking key facial landmarks and providing structured feedback through an intuitive interface.
How we built it
Detectify was developed using Flask for the backend, integrating the Gemini API to assist with facial landmark detection. We used HTML, CSS, and JavaScript to build the frontend interface, aiming for a smooth and simple user experience. Numpy handled data processing, and MongoDB was used to store and retrieve facial data effectively. These technologies worked together to create a seamless system for image analysis and comparison.
Challenges we ran into
Using the Gemini API for landmark detection presented some challenges—especially aligning those landmarks meaningfully for comparison. Integrating multiple tools, from Numpy to MongoDB, required careful coordination, but we managed to get everything working together in the end.
Accomplishments that we’re proud of
We’re proud that Detectify successfully performs facial comparison with landmark-based precision. We also managed to fully integrate MongoDB, giving us the ability to persist data for future analysis. Bringing all the technologies together into a functional, user-friendly system in a short timeframe was a big win for us.
What we learned
We learned a lot about facial recognition systems and the real-world challenges of implementing them. From making sense of facial landmarks using an API, to connecting a live Flask backend with a frontend and database, this project stretched our full-stack development skills in a meaningful way.
What’s next for Detectify
We plan to modernize the UI to make it more polished and user-friendly, and expand the analysis capabilities—like adding similarity scoring, handling multiple faces per image, or even implementing identity validation flows. Long-term, we’re interested in exploring applications in security, forensics, and beyond.
Log in or sign up for Devpost to join the conversation.