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.
- Clone this project:
git clone https://github.com/ErfanMomeniii/face-emotion-recognition.git
- Install the required libraries:
pip install -r requirements.txt
- Download the Kaggle data and store it in the
/dataset/folder. - 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.