Vision#

The Google Cloud Vision (Vision API docs) API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g., “sailboat”, “lion”, “Eiffel Tower”), detects individual objects and faces within images, and finds and reads printed words contained within images. You can build metadata on your image catalog, moderate offensive content, or enable new marketing scenarios through image sentiment analysis. Analyze images uploaded in the request or integrate with your image storage on Google Cloud Storage.

Installation#

Install the google-cloud-vision library using pip:

$ pip install google-cloud-vision

Authentication and Configuration#

  • For an overview of authentication in google-cloud-python, see Authentication.

  • In addition to any authentication configuration, you should also set the GOOGLE_CLOUD_PROJECT environment variable for the project you’d like to interact with. If the GOOGLE_CLOUD_PROJECT environment variable is not present, the project ID from JSON file credentials is used.

    If you are using Google App Engine or Google Compute Engine this will be detected automatically.

  • After configuring your environment, create a ImageAnnotatorClient.

>>> from google.cloud import vision
>>> client = vision.ImageAnnotatorClient()

or pass in credentials explicitly.

>>> from google.cloud import vision
>>> client = vision.ImageAnnotatorClient(
...     credentials=creds,
... )

Annotate an Image#

You can call the annotate_image() method directly:

>>> from google.cloud import vision
>>> client = vision.ImageAnnotatorClient()
>>> response = client.annotate_image({
...   'image': {'source': {'image_uri': 'gs://my-test-bucket/image.jpg'}},
...   'features': [{'type': vision.enums.Feature.Type.FACE_DETECTION}],
... })
>>> len(response.annotations)
2
>>> for face in response.annotations[0].faces:
...     print(face.joy)
Likelihood.VERY_LIKELY
Likelihood.VERY_LIKELY
Likelihood.VERY_LIKELY
>>> for logo in response.annotations[0].logos:
...     print(logo.description)
'google'
'github'

Single-feature Shortcuts#

If you are only requesting a single feature, you may find it easier to ask for it using our direct methods:

>>> from google.cloud import vision
>>> client = vision.ImageAnnotatorClient()
>>> response = client.face_detection({
...   'source': {'image_uri': 'gs://my-test-bucket/image.jpg'},
... })
>>> len(response.annotations)
1
>>> for face in response.annotations[0].faces:
...     print(face.joy)
Likelihood.VERY_LIKELY
Likelihood.VERY_LIKELY
Likelihood.VERY_LIKELY

No results found#

If no results for the detection performed can be extracted from the image, then an empty list is returned. This behavior is similar with all detection types.

Example with logo_detection():

>>> from google.cloud import vision
>>> client = vision.ImageAnnotatorClient()
>>> with open('./image.jpg', 'rb') as image_file:
...     content = image_file.read()
>>> response = client.logo_detection({
...     'content': content,
... })
>>> len(response.annotations)
0

API Reference#

This package includes clients for multiple versions of the Vision API. By default, you will get v1, the latest stable version.

A new beta release with additional features over the current stable version, spelled v1p2beta1, is provided to allow you to use these new features. These are expected to move into the stable release soon; until then, the usual beta admonishment (changes are possible, etc.) applies.

An API and type reference is provided for this beta:

A previous beta release spelled v1p2beta1, is provided as well.

An API and type reference is provided for this beta:

Changelog#

For a list of all google-cloud-vision releases: