This project is a face-based emoji recommendation engine that takes an image of a face as input and recommends an emoji that best matches the emotion shown on the face as well as 4 other face landmarks.
- Clone this repository
- Install the required packages using the following command:
pip install -r requirements.txt- Run the following command to start the application:
python app.py- Open a web browser and navigate to
http://localhost:5002/ - Allow Camera acess
- Or Upload an image of a face.
app.py: The main script that runs the Flask application.templates/: Contains the HTML template and its styles.models/: Contains our pre-trained model for emotion recognition.app_utils.py: Contains utility functions for face landmarks recognition.dataset/: Contains the dataset used to map emojis to emotions and face landmarks as well as the data used to evaluate the emoji recommendation engine.evaluations/: Contains the scripts used to evaluate our trained emotion recognition model as well as deepface.model_utils: Contains the architecture of the emotion recognition model, the data generator, the preprocessing functions, and the training script.monitor: Contains the script to monitor the model's convergence.final_metric.ipynb: Contains the final metric used to evaluate the emoji recommendation engine.requirements.txt: Contains the required packages for this project.assets/: Contains the images used in the README.
Check the project description for more details about the project.
- [Gabriel Mercier]
- [Brahim Touayouch]