CODESEEDSign in
Explore projects
Swiftintermediatemobile

On-device Vision Classifier

iOS application that classifies objects in real-time from the camera using Core ML / Vision framework, completely offline, without API calls.

5 steps

Project steps

  1. 01

    Camera feed

    AVCaptureSession with video frame output at 30fps.

  2. 02

    Vision request

    VNCoreMLRequest on each frame with a MobileNetV3 or EfficientDet model.

  3. 03

    Results overlay

    Bounding boxes and labels drawn with SwiftUI overlay on camera preview.

  4. 04

    Confidence threshold

    Slider to adjust the minimum confidence threshold.

  5. 05

    Custom model

    Option to import a custom .mlpackage model from the Files app.

Recommended resources

Ready to build this?

Fork the repo on GitHub and start building. A mentor will review your code when you open a PR.

5 steps

Tech stack

SwiftSwiftUIVisionCore MLAVFoundation