Google Cloud Vision API Documentation

Cloud Vision API allows developers to easily integrate vision detection features within applications, including image labeling, face and landmark detection, optical character recognition (OCR), and tagging of explicit content.

Quickstart

Before you begin

If you haven't done so already, set up your project and create a Google Cloud Storage bucket, as explained below.

Set up your project

1. In the Cloud Platform Console, go to the Projects page and select or create a new project.
   Go to the Projects page
2. Enable billing for your project.
   Go to the Billing page
3. Enable the Cloud Vision API.
   Enable the API
   You do not need to get credentials after enabling the API.

Create a Cloud Storage bucket

1. In the Cloud Platform Console, go to the Cloud Storage browser.
   Go to the Cloud Storage browser
2. Click Create bucket.
3. In the Create bucket dialog, specify the following attributes:
   • Name: A unique bucket name. Do not include sensitive information in the bucket name, as the bucket namespace is global and publicly visible.
   • Storage class: Standard
   • A location where bucket data will be stored.
4. Click Create.

Make a request to the Cloud Vision API service

1. Download demo-image.jpg. (You may need to right-click the link.)
2. Open the Cloud Platform Console Storage Browser, select a bucket, then click UPLOAD FILES and select the demo-image.jpg file to upload from your local machine to your Cloud Storage bucket.

   

   This is the image file that you just uploaded:

   
3. After the file is uploaded and listed in the Cloud Storage Browser, share the image publicly by clicking the Public link box in the right column of the listing.

   
4. Complete the interactive API Explorer template, below, by replacing bucket in the source→gcsImageUri field with the name of the Cloud Storage bucket where you uploaded the demo-image.jpg file.
   Authorize requests using OAuth 2.0:

   

   

   fields		Selector specifying which fields to include in a partial response. Use fields editor
   Request body	{ "requests": [ { "features": [ { "type": "" -- add a property --maxResults } ] "image": { "source": { "gcsImageUri": "" -- add a property -- } -- add a property --content } -- add a property --imageContext } ] -- add a property -- }
   	Execute without OAuth
5. Click Execute without OAuth to send the request to the service (you may have to click twice). After less than one second (typically), the JSON response appears above.

Congratulations! You've made your first images.annotate request to the Cloud Vision API service.

Clean up

To avoid unnecessary Google Cloud Platform charges, use the Cloud Platform Console to delete your Cloud Storage bucket (and your project) if you do not need them.