MoodMonitor

Inspiration

The inspiration behind MoodMonitor stemmed from the recognition of the immense stress and pressure faced by students during midterm season. We wanted to create a solution that could empower individuals to better understand and manage their emotions, ultimately promoting mental well-being and resilience.

What it does

MoodMonitor utilizes facial recognition technology to analyze users' facial expressions and determine their current emotional state. Based on the detected emotion, the app provides personalized support and resources to help users navigate through challenging times.

We can detect 1 of 7 emotons:

• Neutral
• Happy
• Sad
• Angry
• Disgust
• Surprise
• Fear

How we built it

We built MoodMonitor using Flutter for the front-end development and integrated camera functionality for facial recognition. The back-end processing was implemented using Python libraries for facial recognition and emotion detection.

Challenges we ran into

• It was our first time using Flutter, which is well-known for its steep learning curve and clunky syntax.
• One of the main challenges we encountered was optimizing the performance of the facial recognition algorithm to ensure real-time processing without compromising accuracy.
• Additionally, integrating the front-end and back-end components posed some technical hurdles that we had to overcome.
• We couldn't run the app physically on our phones due to the Wi-Fi connection not allowing public IP access. We had to compromise by running a web version.

Accomplishments that we're proud of

We're proud to have developed a functional prototype of MoodMonitor within the timeframe of the hackathon. Seeing the app accurately detect and respond to users' emotions was a significant accomplishment for our team.

What we learned

Through the development of MoodMonitor, we gained valuable insights into facial recognition technology and its applications in mental health support. We also honed our skills in cross-platform app development and project management.

What's next for MoodMonitor

In the future, we envision expanding MoodMonitor to include additional features such as mood tracking, mindfulness exercises, and personalized mental health resources. We also plan to conduct further testing and refinement to enhance the accuracy and effectiveness of the emotion detection algorithm. Additionally, we aim to explore partnerships with mental health organizations to reach a wider audience and make a positive impact on student well-being. Some Ideas:

• Open/block certain apps based on your mood
• Improve the training data quantity and quality.
• More interactive/useful screens for every emotion's page

Built With

• dart
• deepface
• fastapi
• flutter
• python