Introduction
Hybrid & On-prem
Hybrid cloud
Cloud data overview
Restrict data access by IP range
How to generate signed URLs
How to generate non-expiring signed URLs
On-prem
App
Overview
Ontology management
Projects
Data import
Labeling guides
Label export
Members
Workforce
Quality assurance
Automation
Model-assisted labeling
MAL import formats
Webhooks setup
Queue system
Real-time human-in-the-loop labeling
Custom label interface
Images
Videos
Text
Geospatial data
Python SDK
Getting started
Creating your first project
Project setup script
Projects
Datasets
Data Rows
Import annotations
Labels
General concepts
Python SDK FAQ
API reference
Model-assisted labeling Python script
GraphQL API
Intro to the GraphQL API
Getting started
Data types overview
Ontologies
Datasets
Data Rows
Bulk import requests
Labeling parameters
Labels
Members
Attachments
Review queue
Webhooks
Legacy editor
Migration guide
Legacy vs new editor ontology
Legacy vs new editor JSON exports
Legacy vs new editor hotkeys
Model predictions (legacy)
Multistep labeling
Release notes
Release definitions
January 6, 2021
December 7, 2020
November 4, 2020
October 9, 2020
September 25, 2020
August 21, 2020
August 6, 2020
July 6, 2020
June 22, 2020
June 2, 2020
May 19, 2020
April 14, 2020
April 1, 2020
March 3, 2020
February 18, 2020
February 5, 2020
January 17, 2020
Terms of use
Table of Contents
- All Categories
- Images
- Image classification
Image classification
Updated
by Alex Cota
You can use the Image classification tool to create a global or nested Classification on an Object. The classification tool only produces a semantic classification and does not include any geometric annotation or per-pixel classification information. To learn how to apply Classifications to video or text data see, Video classification and Text classification.
There are four classification types:
- Radio: Use the radio format if you would like a labeler to choose a single answer from a selection of answer choices. The nested radio format allows the labeler to select or search for an answer at each level.
- Checklist: Use the checklist format if you would like a labeler to choose multiple answers from a selection of answer choices.
- Dropdown: The nested dropdown allows labelers to select answers from a nested taxonomy.
- Free-form text: Use the text classification format if you would like a labeler to enter a free-form text answer in response to a classification question.
Import image data
To learn how to import your images directly, see Direct upload. To learn how to import your images URLs via JSON, see Import via JSON. To learn how to attach metadata to your imported images, see Asset metadata via JSON.
To learn how to import programmatically, see Bulk add data rows.
Set up global classification
A global classification on an image provides useful metadata about the image itself.

- Bypass the "Add Object" step.
- Add a classification question(s).
- Select answer choice type and add answer(s).
- Click "Confirm".
Set up nested classification on an object
A nested classification provides additional information on an Object (e.g. a Radio classification on a Mask object).

- Click "Add Object".
- Name your object and choose a labeling tool from the dropdown menu.
- Click on the right arrow on the object to open the Settings for that object.
- Add a classification question(s).
- Select answer choice type and add answer(s).
- Click "Done".
To see a sample script for setting up your project’s ontology programmatically, see Project setup script.
Searchable radio answers
When you create a radio classification question in your ontology, you have the option to enable autocomplete on the answers by toggling on the "Searchable" feature. When "searchable" is on, your labelers can type in the answer they are looking for instead of having to scroll through a long list of answers to find the one they are looking for.
Note: Enabling autocomplete will disable the hotkeys for that radio classification. To enable hotkeys again, toggle off "searchable".

Label format
To learn how to export your annotations, see How to export labels. To see a sample export for Classifications see Label export formats.