Label images with the Cloud Vision API
Label images with the Cloud Vision API
Introduction
This tutorial walks you through a basic application that uses the Vision API.
In this application, a LABEL_DETECTION request annotates an image with a
label (tag) that is selected based on the image content. For example, a
picture of a barn may produce a label of barn, farm, or some other similar
annotation.
Project setup
GCP organizes resources into projects. This allows you to collect all of the related resources for a single application in one place.
Begin by creating a new project or selecting an existing project for this tutorial.
For details, see Creating a project.
Enable the Vision API
Before your project can use a service like the Vision API, you must enable the API for the project.
Use the following to enable the API:
Open Cloud Shell
In this tutorial, you do much of your work in Cloud Shell, which is a built-in command-line tool for the GCP Console.
Open Cloud Shell by clicking the
Clone the sample code
Use Cloud Shell to clone and navigate to the sample code. The sample code is cloned from your project repository to the Cloud Shell.
rm -rf python-docs-samples
Clone the sample repository:
git clone https://github.com/GoogleCloudPlatform/python-docs-samples.git
Change directory to the tutorial directory:
cd python-docs-samples/vision/cloud-client/quickstart
You are now in the main directory for the sample code.
Explore the application
Enter the following command to view the application code:
cat quickstart.py
The quickstart.py file formats your request information, like the request type
and content. Expand each section below to learn about the details.
Requests to the Vision API are provided as JSON objects. See the
Vision API reference for complete information on the specific
structure of such a request. Your JSON request is only sent when you call
execute. This pattern allows you to pass around such requests and call
execute as needed.
Set up up a service account and credentials
To use a Cloud API, you need to set up the proper credentials for your application. This enables your application to authenticate its identity to the service and obtain authorization to perform tasks.
Create a service account
You need to create a service account to authenticate your API requests. If you already have the service account created, it will be reused.
gcloud iam service-accounts create vision-quickstart --project
Create credentials
Next, create a service account key and set it as your default credentials.
gcloud iam service-accounts keys create key.json --iam-account \
vision-quickstart@.iam.gserviceaccount.com
export GOOGLE_APPLICATION_CREDENTIALS=key.json
Test your app
To test your app with a sample image, enter the following command:
python quickstart.py
The image resource, resources/wakeupcat.jpg, is specified in the source.
(View image)
Conclusion
Congratulations! You are ready to use the Cloud Vision API.
Here's what you can do next:
- Work through the face detection tutorial.
- Try the document text tutorial.
- See the sample applications.
- Download the Google Cloud SDK to run on your local machine.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see our Site Policies. Java is a registered trademark of Oracle and/or its affiliates.