This web application integrates computer vision using TensorFlow.js into the SvelteKit framework. The project showcases two machine learning features: Image Classification and Real-Time Object Detection.
-
Image Classification: Utilizing a pre-trained MobileNet model, the application accurately classifies images, recognizing a wide range of objects.
-
Real-Time Object Detection: The app leverages the COCO-SSD (Common Objects in Context - Single Shot MultiBox Detector) model to detect and locate objects in a live webcam stream, overlaying bounding boxes for an interactive experience.
Explore the live demo: Computer Vision in SvelteKit
-
SvelteKit
-
TensorFlow.js
-
MobileNet
-
COCO-SSD
-
Installation: Clone this repository to your local machine and install the necessary dependencies:
git clone https://github.com/fadhlakmal/tfjs-sveltekit-app.git cd cv-sveltekit-app npm install
-
Run and Explore the App: Start the SvelteKit development server to run the app locally:
npm run dev -- --open
Feel free to modify and expand upon this project to suit your specific needs.
Contributions to this project are welcome! If you have ideas for improvements or new features, feel free to reach out through GitHub issues or by email.
This project is licensed under the MIT License.