This repository contains the implementation of a research paper on Facial Expression Recognition (FER) using Deep Convolutional Neural Networks (DCNN). The research focuses on analyzing different algorithms for FER and presents a comparative analysis.
- DCNN_test.ipynb: Jupyter notebook containing the implementation of the DCNN model for FER.
- GPU_Plots.ipynb: Jupyter notebook for plotting performance metrics using GPU data.
- helper_functions.py: Python script containing helper functions for data processing and model training.
- docs: Directory containing relevant documentation and presentations related to the research.
- Comparative Analysis of Facial Expression Recognition Algorithms(IDSCS).pdf: Research paper PDF.
- Facial Emotion Recognition using DCNN architecture.pdf: Another research paper PDF.
- IEEE Access DCNN.pdf: Additional research paper PDF.
- history_var: Directory storing training history variables for different experiments.
- model.h5: Trained model file.
- model.png: Image of the model architecture.
- model_architecture.png: Another image depicting the model architecture.
- output.png: Output image.
- paper: Directory containing research paper drafts and comparative analysis documents.
- Comparative Analysis of Facial Expression Recognition Algorithms(ICSDS).docx: Research paper draft.
- Comparative Analysis of Facial Expression Recognition Algorithms_IEANG.docx: Another research paper draft.
- plot_model: Directory containing plots generated during model training and evaluation.
- GPU_Comparision.png: Plot comparing GPU performance.
- accuracy-dcnn.png: Accuracy plot.
- loss-dcnn.png: Loss plot.
- val_acc.png: Validation accuracy plot.
- val_loss.png: Validation loss plot.
- tensoroard: Directory for storing TensorBoard logs.
- time_var: Directory storing timing variables for different experiments.
Contributions to this repository are welcome. If you find any issues or have suggestions for improvements, please open an issue or submit a pull request.