MicroSense: The Micro Expression Detector is a deep learning-based project designed to detect micro-expressions in video uploads. Micro-expressions are brief, involuntary facial expressions that reveal true emotions. This tool can be used for various applications, including psychological studies, security, and improving human-computer interaction.
- Detects micro-expressions in uploaded videos.
- Trained using the YOLO object detection algorithm.
- Model trained on over 10,000 examples and more than 10 different micro-expressions.
- High accuracy in detecting subtle facial expressions.
- User-friendly interface for video upload and analysis.
-
Clone the repository
git clone https://github.com/zaibreyaz/MicroSense.git
-
Make sure you have python 3.11 and pip installed in your machine.
-
Install the required dependencies using pip:
pip install -r requirements.txt
-
Run the flask application:
pyhton app.py
- Real-time Processing: Explore the implementation of real-time micro-expression detection from video streams to enhance usability in live scenarios.
- Cross-Dataset Evaluation: Validate the model's performance across different datasets to ensure robustness and generalizability.
- Multi-Modal Analysis: Integrate additional data modalities, such as audio or text, to provide a more comprehensive analysis of micro-expressions in context.
- User Customization: Allow users to customize detection thresholds and settings based on specific use cases or environments.
- Mobile Deployment: Investigate options for deploying the model on mobile devices to make micro-expression detection accessible on-the-go.
These enhancements aim to improve the utility, accessibility, and accuracy of the MicroSense project, making it a valuable resource for various fields.
We welcome contributions! Please read our CONTRIBUTING.md file for guidelines on how to contribute to this project.
This project is licensed under the MIT License. See the LICENSE file for details.
If you have any questions or need further assistance, please contact our support team at [email protected].
Client: HTML, CSS, JavaScript
Server: Flask, Sqlalchemy, Python
Object Detection: YOLO