With Cloud Vision's image labeling APIs, you can recognize entities in an image without having to provide any additional contextual metadata.
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.
|High-accuracy image labeling||
Firebase ML's image labeling API is powered by Google Cloud's industry-leading image understanding capability, which can classify images with 10,000+ labels in many categories. (See below.)
Try it yourself with the Cloud Vision API demo.
|Knowledge Graph entity support||
In addition the text description of each label that Firebase ML 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.
|Limited free use||
Free for first 1000 uses of this feature per month: see Pricing
The image labeling API supports 10,000+ labels, including the following examples and many more:
|Category||Example labels||Category||Example labels|
|Arts & entertainment||
|Business & industrial||
||Home & garden||
||Modes of transport||
|Label||Knowledge Graph entity ID||Confidence|
|soccer specific stadium||/m/0404y4||0.95806926|