Emotion Detector

• 

  Emotional Damage

Inspiration

Approximately 12 million people 40 years and over in the United States have vision impairment, including 1 million who are blind. For this reason, they cannot see the facial and corporal expressions that help convey our emotions.

What it does## What it does

Through the use of ML and computer vision, this pre-trained program is capable of detecting ASL sign language and outputting the translation to the user in real time.

How we built it

We trained and built model using TensorFlow. To detect keypoints of palms, hands and face we used Mediapipe. Then we use that keypoints to predict human emotions

Challenges we ran into

The biggest challenge was to find proper ASL dataset of different words to train for making the ASL model.

Accomplishments that we're proud of

We are able build a model to predict human emotion and body language with good accuracy.

What we learned

We learned how to detect human emotion, body language and American Sign Language in computer vision.

What's next for Untitled

We want to build the ASL model properly with bigger dataset and increase our accuracy.

Built With

• machine-learning
• python