https://github.com/anvesham/facial_emotion_recognition
Project aimed to compare the performances of MLP, SVM and CNN algorithms in detecting the facial emotions. It also uses a pre-trained model and evaluates its performance in facial emotion recognition.
https://github.com/anvesham/facial_emotion_recognition
cnn facial-emotion-recognition haarcascade-frontalface hog-features mlp pretrained-models python pytorch sift-descriptors svm youtube-video
Last synced: 7 months ago
JSON representation
Project aimed to compare the performances of MLP, SVM and CNN algorithms in detecting the facial emotions. It also uses a pre-trained model and evaluates its performance in facial emotion recognition.
- Host: GitHub
- URL: https://github.com/anvesham/facial_emotion_recognition
- Owner: AnveshaM
- Created: 2022-07-06T17:28:13.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-07-06T17:48:38.000Z (over 3 years ago)
- Last Synced: 2025-01-16T02:25:34.572Z (9 months ago)
- Topics: cnn, facial-emotion-recognition, haarcascade-frontalface, hog-features, mlp, pretrained-models, python, pytorch, sift-descriptors, svm, youtube-video
- Language: Jupyter Notebook
- Homepage:
- Size: 2.27 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Facial_Emotion_Recognition
Project aimed to compare the performances of MLP, SVM and CNN algorithms in detecting the facial emotions. It also uses a pre-trained model and evaluates its performance in facial emotion recognition. The highest accuracy was achieved by the pretrained CNN model in detecting emotions.
Dataset -
RAF Dataset
File Contents -
1. SVM_MLP_Train.ipynb - Google Colaboratory file to train MLP and SVM models. Both models are tried with different combinations of feature descriptors like SIFT, and HOG.
2. CNN_Train.ipynb - Google Colaboratory file to construct and train a Convolutional Neural Network.
3. Test_Emotion_Recognition_RAFDataset_SVM_MLP.ipynb - Google Colaboratory file to test the MLP, SVM and CNN models on the test RAF dataset and note down the accuracies of the models.
4. Test_Emotion_Recognition_Video_CNN.ipynb - Google Colaboratory file to test the MLP, SVM and CNN models on a YouTube video.