Image Labeling
With ML Kit's image labeling APIs, you can recognize entities in an image without having to provide any additional contextual metadata, using either an on-device API or a cloud-based API.
Image labeling gives you insight into the content of images. When you use the API, you get a list of the entities that were recognized: people, things, places, activities, and so on. Each label found comes with a score that indicates the confidence the ML model has in its relevance. With this information, you can perform tasks such as automatic metadata generation and content moderation.
If you're a Flutter developer, you might be interested in FlutterFire, which includes a plugin for Firebase's ML Vision APIs.
Choose between on-device and Cloud APIs
| On-device | Cloud | |
|---|---|---|
| Pricing | Free | Free for first 1000 uses of this feature per month: see Pricing |
| Label coverage |
400+ labels that cover the most commonly-found concepts in photos. See below. |
10,000+ labels in many categories. See below. Also, try the Cloud Vision API demo to see what labels can be found for an image you provide. |
| Knowledge Graph entity ID support |
Example on-device labels
The device-based API supports 400+ labels, such as the following examples:
| Category | Example labels |
|---|---|
| People | CrowdSelfieSmile |
| Activities | DancingEatingSurfing |
| Things | CarPianoReceipt |
| Animals | BirdCatDog |
| Plants | FlowerFruitVegetable |
| Places | BeachLakeMountain |
Example cloud labels
The cloud-based API supports 10,000+ labels, such as the following examples:
| Category | Example labels | Category | Example labels |
|---|---|---|---|
| Arts & entertainment | SculptureMusical InstrumentDance |
Astronomical objects | CometGalaxyStar |
| Business & industrial | RestaurantFactoryAirline |
Colors | RedGreenBlue |
| Design | FloralPatternWood Stain |
Drink | CoffeeTeaMilk |
| Events | MeetingPicnicVacation |
Fictional characters | Santa ClausSuperheroMythical creature |
| Food | CasseroleFruitPotato chip |
Home & garden | Laundry basketDishwasherFountain |
| Activities | WeddingDancingMotorsport |
Materials | CeramicTextileFiber |
| Media | NewsprintDocumentSign |
Modes of transport | AircraftMotorcycleSubway |
| Occupations | ActorFloristPolice |
Organisms | PlantAnimalFungus |
| Organizations | GovernmentClubCollege |
Places | AirportMountainTent |
| Technology | RobotComputerSolar panel |
Things | BicyclePipeDoll |
Google Knowledge Graph entity IDs
In addition the text description of each label that ML Kit returns, it also returns the label's Google Knowledge Graph entity ID. This ID is a string that uniquely identifies the entity represented by the label, and is the same ID used by the Knowledge Graph Search API. You can use this string to identify an entity across languages, and independently of the formatting of the text description.
Example results
| On-device | Cloud |
|---|---|
|
Description
Stadium
Knowledge Graph entity ID
/m/019cfy
Confidence
0.9205354
Description
Sports
Knowledge Graph entity ID
/m/06ntj
Confidence
0.7531109
Description
Event
Knowledge Graph entity ID
/m/081pkj
Confidence
0.66905296
Description
Leisure
Knowledge Graph entity ID
/m/04g3r
Confidence
0.59904146
Description
Soccer
Knowledge Graph entity ID
/m/02vx4
Confidence
0.56384534
Description
Net
Knowledge Graph entity ID
/m/02qdwbp
Confidence
0.54679185
Description
Plant
Knowledge Graph entity ID
/m/05s2s
Confidence
0.524364
... etc. |
Description
sport venue
Knowledge Graph entity ID
/m/0bmgjqz
Confidence
0.9860726
Description
player
Knowledge Graph entity ID
/m/02vzx9
Confidence
0.9797604
Description
stadium
Knowledge Graph entity ID
/m/019cfy
Confidence
0.9635762
Description
soccer specific stadium
Knowledge Graph entity ID
/m/0404y4
Confidence
0.95806926
Description
football player
Knowledge Graph entity ID
/m/0gl2ny2
Confidence
0.9510419
Description
sports
Knowledge Graph entity ID
/m/06ntj
Confidence
0.9253524
Description
soccer player
Knowledge Graph entity ID
/m/0pcq81q
Confidence
0.9033665
Description
arena
Knowledge Graph entity ID
/m/018lrm
Confidence
0.8897188
... etc. |