Skip to content

ofbennett/WhatIsIt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WhatIsIt

An iOS app using CoreML to identify objects in images

Requires: Xcode 11 + Swift 5

Overview

A simple swift iOS app that uses the MobileNetV2 model for object detection in images. The user can take photos and the on-device model predicts the dominant object in the image. No internet connection required. Currently the top 6 predictions are displayed to the user along with the associated prediction confidence. The image and predictions can be saved to CoreData for later retreival.

If the model produces a prediction with high confidence the app will vocalise the result :)

To Do

  • Add a settings view to control user preferences
  • Add the ability to choose different models for predicting objects

About

An iOS phone app using computer vision and CoreML to identify objects in images

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages