Image Labeling to Classify Photos and Videos | Fritz AI

Image Labeling

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

Custom Image Segmentation

Quickly move from an idea to a production-ready Image Segmentation model with Fritz AI.

Pre-Trained Image Labeling Models

Add Image Labeling features to iOS and Android apps with pre-trained models and only a few lines of code.

Mobile Image Labeling

Predicted Labels

  • American Black Bear
  • Abacus
  • Abaya
  • Accordion
  • Acorn
  • Acoustic Guitar
  • Aircraft Carrier
  • Airplane
  • Alligator
  • Altar
  • Ambulance
  • Amphibian
  • Ant
  • Anteaters
  • Antelope
  • Ape
  • Apple
  • Apron
  • Armadillo
  • Artichoke
  • Atm
  • Baboon
  • Backpack
  • Badget
  • Bagel
  • Bakery
  • Balance Beam
  • Ball
  • Balloon
  • Banana
  • Band Aid
  • Banjo
  • Bannister
  • Barbell
  • Barber Chair
  • Barbershop
  • Barn
  • Barometer
  • Barrel
  • Barrow
  • Baseball
  • Baseball Player
  • Basketball
  • Bassinet
  • Bassoon
  • Bathing Suit
  • Bathtub
  • Beach
  • Beacon
  • Beaker
  • Bear
  • Bearskin
  • Beaver
  • Bed
  • Bee
  • Bee House
  • Beetle
  • Bell Cote
  • Bell Pepper
  • Bib
  • Bicycle
  • Bikini
  • Binder
  • Binoculars
  • Bird
  • Birdhouse
  • Bison
  • Blimp
  • Blue Jeans
  • Boar
  • Boat
  • Boathouse
  • Bobsled
  • Bolo Tie
  • Bonnet
  • Book
  • Bookcase
  • Bookshop
  • Bottle
  • View all 681 labels

Getting Started

import Fritz

let labelModel = FritzVisionLabelModelFast()

let image = FritzVisionImage(image: uiImage)

guard let labels = try? labelModel.predict(image) else { return }
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.

Features

Labels for Everything

Our pre-trained models are trained on millions of images and make predictions with hundreds of labels.

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

Architecture

MobileNet V2 variant

Model Size

~13 MB

FLOPS

300 M

Input

224x224-pixel image

Output

Class label prediction

Confidence score (0-100%)

Formats

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

Benchmarks

38 FPS on iPhone X

10 FPS on Pixel 2