This project is an implementation of facial emotion recognition using convolutional neural networks. It is capable of detecting and categorizing facial emotions into the following categories:

• Angry
• Disgusted
• Fearful
• Happy
• Neutral
• Sad
• Surprised

For training models, I utilized Kaggle data. The prediction accuracy of the models is above 87 percent, as shown below:

You can improve the accuracy by adjusting hyperparameters or implementing data augmentation techniques.

1. Clone this project:

git clone https://github.com/ErfanMomeniii/face-emotion-recognition.git

2. Install the required libraries:

pip install -r requirements.txt

3. Download the Kaggle data and store it in the /dataset/ folder.
4. Train the model and run it to capture and recognize facial emotions:

python face-emotion-recognition.py

Data source: Emotion Detection FER Dataset

• Facial Emotion Recognition Using Deep Convolutional Neural Networks
• Facial Expression Recognition Using Convolution Neural Networks
• Facial Emotion Recognition Based on Convolutional Neural Networks

face-emotion-recognition is released under MIT License.