Inspiration
Our inspiration for this project came from the challenges faced by international students and those with darker skin tones at Mason Korea, who struggle to access their dormitories due to the facial detection systems being trained primarily on Korean faces. We recognized the need for a more inclusive system that could recognize faces of all races and ethnicities, ensuring that everyone has equal access to their living spaces.
What it does
Our system, built using Arduino hardware and Python with OpenCV software, is designed to recognize faces of all races and ethnicities, regardless of skin tone or facial structure. It provides accurate and reliable facial detection, ensuring that all students at Mason Korea can easily access their dormitories without facing the limitations of the current systems.
How we built it
We trained our system using a diverse dataset that included faces of various races and ethnicities. This involved fine-tuning the facial recognition algorithm to ensure that it could accurately detect and recognize faces that may not conform to the Korean facial structure. We then integrated this algorithm into the Arduino hardware, allowing for real-time facial detection and access control.
Challenges we ran into
One of the main challenges we faced was ensuring that our system could accurately detect faces of all races and ethnicities, especially those with darker skin tones. We also had to overcome technical challenges in integrating the Arduino hardware with the facial recognition algorithm and ensuring reliable performance in real-world scenarios.
Accomplishments that we're proud of
We're proud to have developed a system that addresses an important issue faced by the international student community at Mason Korea. Our system not only provides a solution to the current limitations of the facial detection systems but also showcases the potential of technology to promote inclusivity and equal access.
What we learned
Through this project, we learned about the complexities of facial recognition in training datasets. We also gained valuable experience in developing technology that addresses real-world challenges and has a positive impact on people's lives.
What's next for our project
In the future, we plan to further refine and optimize our system to improve its accuracy and reliability. We also aim to expand its capabilities to include additional features that enhance the overall security and convenience of dormitory access for all students at Mason Korea.
Log in or sign up for Devpost to join the conversation.