Emoji Generator from Facial Expressions using CNN

This project uses a Convolutional Neural Network (CNN) to recognize human facial expressions from grayscale images and maps the detected emotion to a representative emoji (e.g., πŸ˜€ for Happy, 😒 for Sad, 😠 for Angry).

Model Info

  • Framework: TensorFlow / Keras
  • Input: 48x48 grayscale facial image
  • Output: Predicted emotion label mapped to an emoji
  • Model Format: .keras
  • Dataset: FER-2013

Emotion to Emoji Mapping

0 β†’ Angry 
1 β†’ Disgust  
2 β†’ Fear 
3 β†’ Happy  
4 β†’ Neutral 
5 β†’ Sad  
6 β†’ Surprise
Downloads last month
7
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Evaluation results