This project is a simple demonstration of using TensorFlow.js's Face landmark detection to acheive simple SnapChat-like filters in the browser, allowing the user to take a snapshot and save the end result.
This project is a work in progress...
- Improve this README
- Update CSS ID's and class names for components
- Improve component styling
- Get webcam stream and display it back to the user
- Get webcam stream and display it back to the user
To install the project, run:
npm install
This will install all the necessary dependencies listed in the package.json file.
To build the project, run:
npm run build
This will use Parcel to bundle the project and output the result in the dist directory.
To start the development server, run:
npm run dev
This will start a Parcel development server with hot module replacement.
This project uses several dependencies:
- TensorFlow.js and its CPU and WebGL backends for running the object detection model.
- The COCO-SSD model for object detection.
- Parcel for bundling the project.
- Sass for styling.
- License:
- This project is licensed under the MIT license.