metadata
language: en
license: mit
tags:
- keras
- cnn
- facial-expression
- emoji
- image-classification
- emotion-detection
model-index:
- name: Emoji Generator from Facial Expression
results:
- task:
type: image-classification
name: Facial Emotion Classification
dataset:
name: FER-2013
type: fer2013
metrics:
- name: Accuracy
type: accuracy
value: 0.83
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., 😀 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 → Angry
1 → Disgust
2 → Fear
3 → Happy
4 → Neutral
5 → Sad
6 → Surprise