Discover is a visionOS application for users to detect objects in an image using machine learning models from Hugging Face. In Discover, users can select an image from their photo library or capture an image in real-time and send it to the AWS server to detect the objects in that image. They can also send a question by talking to the headset where speech recognition will be applied to get a result back from the server.
- User can select an image from the photo library
- User can capture an image using the main camera from the Apple Vision Pro
- Send the image to AWS Lambda Server via Websocket
- Receive the response from the server and display the result to user
- Talk to the headset and apply speech recognition to send a question to the server
- Receive the result from the server and display it to the user