Image Labeling to Classify Photos and Videos | Fritz AI

Image Labeling

Use Image Labeling to recognize people, places, and things in your app. This computer vision model understands a collection of hundreds of labels.

Getting Started

import Fritz

var labelModel: FritzVisionLabelModel?

let image = FritzVisionImage(image: uiImage)

labelModel.predict(image) { results, error in
  guard error == nil, let labels = result else { return }

  // Code to use predicted labels here...
Image Labeling

The Swift code sample here illustrates how simple it can be to use image labeling in your app. Use the links below to access additional documentation, code samples, and tutorials that will help you get started.


Supports 681 Labels

Trained on millions of images, Image Labeling makes predictions such as:

Model Variants

Fast: Optimized for speed, best for processing video streams in real-time or on older devices.

Accurate: Optimized for higher accuracy where prediction quality is more important than speed.

Small: Optimized for size, keep your application bundle size low and conserve bandwidth.

Runs On-Device

All predictions / model inferences are made completely on-device.

No internet connection is required to interpret images or video.

No internet dependency means super-fast performance.

Cross-Platform SDKs

Supported mobile platforms:

  • Android Image Labeling
  • iOS Image Labeling
Live Video Performance

Runs on live video with a fast frame rate.

Exact FPS performance varies depending on device, but it is possible to run this feature on live video on modern mobile devices.

Technical Specifications


MobileNet V2 variant

Model Size

~13 MB


300 M


224x224-pixel image


Class label prediction

Confidence score (0-100%)


Core ML, TensorFlow, TensorFlow Lite, TensorFlow Mobile, Keras


38 FPS on iPhone X

10 FPS on Pixel 2