Extract, Analyze, and Translate Text from Images with the Cloud ML APIs
In this lab, we'll explore the power of machine learning by using multiple machine learning APIs together. We'll start with the Cloud Vision API's text detection method to make use of Optical Character Recognition (OCR) to extract text from images. Then we'll learn how to translate that text with the Translation API and analyze it with the Natural Language API.
What you'll learn
Creating a Vision API request and calling the API with curl
Using the text detection (OCR) method of the Vision API
Using the Translation API to translate text from your image
Using the Natural Language API to analyze the text
Setup and Requirements
Before you click the Start Lab button
Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources will be made available to you.
This hands-on lab lets you do the lab activities yourself in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials that you use to sign in and access Google Cloud for the duration of the lab.
To complete this lab, you need:
- Access to a standard internet browser (Chrome browser recommended).
- Time to complete the lab---remember, once you start, you cannot pause a lab.
How to start your lab and sign in to the Google Cloud Console
Click the Start Lab button. If you need to pay for the lab, a pop-up opens for you to select your payment method. On the left is the Lab Details panel with the following:
- The Open Google Console button
- Time remaining
- The temporary credentials that you must use for this lab
- Other information, if needed, to step through this lab
Click Open Google Console. The lab spins up resources, and then opens another tab that shows the Sign in page.
Tip: Arrange the tabs in separate windows, side-by-side.
Note: If you see the Choose an account dialog, click Use Another Account.
If necessary, copy the Username from the Lab Details panel and paste it into the Sign in dialog. Click Next.
Copy the Password from the Lab Details panel and paste it into the Welcome dialog. Click Next.
Important: You must use the credentials from the left panel. Do not use your Google Cloud Skills Boost credentials. Note: Using your own Google Cloud account for this lab may incur extra charges.
Click through the subsequent pages:
- Accept the terms and conditions.
- Do not add recovery options or two-factor authentication (because this is a temporary account).
- Do not sign up for free trials.
After a few moments, the Cloud Console opens in this tab.
Activate Cloud Shell
Cloud Shell is a virtual machine that is loaded with development tools. It offers a persistent 5GB home directory and runs on the Google Cloud. Cloud Shell provides command-line access to your Google Cloud resources.
- In the Cloud Console, in the top right toolbar, click the Activate Cloud Shell button.
- Click Continue.
It takes a few moments to provision and connect to the environment. When you are connected, you are already authenticated, and the project is set to your PROJECT_ID. The output contains a line that declares the PROJECT_ID for this session:
gcloud is the command-line tool for Google Cloud. It comes pre-installed on Cloud Shell and supports tab-completion.
(Optional) You can list the active account name with this command:
(Optional) You can list the project ID with this command:
gcloud, in Google Cloud, Cloud SDK documentation, see the gcloud command-line tool overview.
Create an API Key
Since you'll be using
curl to send a request to the Vision API, you'll need to generate an API key to pass in your request URL. To create an API key, navigate to:
Navigation Menu > APIs & services > Credentials:
Click + Create Credentials.
In the drop down menu, select API key:
Next, copy the key you just generated. Click Close.
Now save the API key to an environment variable to avoid having to insert the value of your API key in each request.
Run the following in Cloud Shell, replacing
<your_api_key> with the key you just copied.
Upload an image to a cloud storage bucket
Creating a Cloud Storage bucket
There are two ways to send an image to the Vision API for image detection: by sending the API a base64 encoded image string, or passing it the URL of a file stored in Cloud Storage. For this lab you'll create a Cloud Storage bucket to store your images.
Navigate to the Navigation menu > Cloud Storage browser in the Console:
Then click Create bucket.
Give your bucket a globally unique name and click on Choose how to control access to objects.
Uncheck the box for Enforce public access prevention on this bucket.
Choose Fine-grained under Access Control and click Create
Upload an image to your bucket
Right click on the following image of a French sign, then click Save image as and save it to your computer as sign.jpg.
Navigate to the bucket you just created in the cloud storage browser and click Upload files. Then select sign.jpg.
Next you'll allow the file to be viewed publicly while keeping the access to the bucket private.
Click on the 3 dots for the image file:
Select Edit Permissions.
Click Add Entry and set the following:
- Select Public for the Entity.
- Ensure allUsers is the value for the Name.
- Select Reader for the Access.
You'll now see that the file has public access.
Now that you have the file in your bucket, you're ready to create a Vision API request, passing it the URL of this picture.
Create your Vision API request
In your Cloud Shell environment, create an
ocr-request.json files, then add the code below to the file, replacing my-bucket-name with the name of the bucket you created. You can create the file using one of your preferred command line editors (
emacs) or click the pencil icon to open the code editor in Cloud Shell:
Add the following to your
You're going to use the TEXT_DETECTION feature of the Vision API. This will run optical character recognition (OCR) on the image to extract text.
Call the Vision API's text detection method
In Cloud Shell, call the Vision API with
The first part of your response should look like the following:
The OCR method is able to extract lots of text from our image, cool! Let's break down the response. The first piece of data you get back from
textAnnotations is the entire block of text the API found in the image. This includes the language code (in this case fr for French), a string of the text, and a bounding box indicating where the text was found in our image. Then you get an object for each word found in the text with a bounding box for that specific word.
Unless you speak French you probably don't know what this says. The next step is translation.
Run the following
curl command to save the response to an
ocr-response.json file so it can be referenced later:
Sending text from the image to the Translation API
The Translation API can translate text into 100+ languages. It can also detect the language of the input text. To translate the French text into English, all you need to do is pass the text and the language code for the target language (en-US) to the Translation API.
First, create a
translation-request.json file and add the following to it:
q is where you'll pass the string to translate.
Save the file.
Run this Bash command in Cloud Shell to extract the image text from the previous step and copy it into a new
translation-request.json (all in one command):
Now you're ready to call the Translation API. This command will also copy the response into a
Run this command to inspect the file with the Translation API response:
Awesome, you can understand more of what the sign said!
In the response,
translatedText contains the resulting translation, and
fr, the ISO language code for French. The Translation API supports 100+ languages, all of which are listed here.
In addition to translating the text from our image, you might want to do more analysis on it. That's where the Natural Language API comes in handy. Onward to the next step!
Analyzing the image's text with the Natural Language API
The Natural Language API helps us understand text by extracting entities, analyzing sentiment and syntax, and classifying text into categories. Use the
analyzeEntities method to see what entities the Natural Language API can find in the text from your image.
To set up the API request, create a
nl-request.json file with the following:
In the request, you're telling the Natural Language API about the text you're sending:
type: Supported type values are
content: pass the text to send to the Natural Language API for analysis. The Natural Language API also supports sending files stored in Cloud Storage for text processing. To send a file from Cloud Storage, you would replace
gcsContentUri and use the value of the text file's uri in Cloud Storage.
encodingType: tells the API which type of text encoding to use when processing the text. The API will use this to calculate where specific entities appear in the text.
Run this Bash command in Cloud Shell to copy the translated text into the content block of the Natural Language API request:
nl-request.json file now contains the translated English text from the original image. Time to analyze it!
analyzeEntities endpoint of the Natural Language API with this
If you scroll through the response you can see the entities the Natural Language API found:
For entities that have a wikipedia page, the API provides metadata including the URL of that page along with the entity's
mid is an ID that maps to this entity in Google's Knowledge Graph. To get more information on it, you could call the Knowledge Graph API, passing it this ID. For all entities, the Natural Language API tells us the places it appeared in the text (
type of entity, and
salience (a [0,1] range indicating how important the entity is to the text as a whole). In addition to English, the Natural Language API also supports the languages listed here.
Looking at this image it's relatively easy for us to pick out the important entities, but if we had a library of thousands of images this would be much more difficult. OCR, translation, and natural language processing can help to extract meaning from large datasets of images.
You've learned how to combine 3 different machine learning APIs: the Vision API's OCR method extracted text from an image, then the Translation API translated that text to English and the Natural Language API to found entities in that text.
What was covered
- Use cases for combining multiple machine learning APIs
- Creating a Vision API OCR request and calling the API with curl
- Translating text with the Translation API
- Extract entities from text with the Natural Language API
Finish your quest
This self-paced lab is part of the Machine Learning APIs and Intro to ML: Image Processing Quests. A Quest is a series of related labs that form a learning path. Completing a Quest earns you a badge to recognize your achievement. You can make your badge (or badges) public and link to them in your online resume or social media account. Enroll in these Quests and get immediate completion credit if you've taken this lab. See other available Quests.
Take your next lab
Try out another lab on Machine Learning APIs, like Classify Text into Categories using the Natural Language API or Awwvision: Cloud Vision API from a Kubernetes Cluster.
Google Cloud Training & Certification
...helps you make the most of Google Cloud technologies. Our classes include technical skills and best practices to help you get up to speed quickly and continue your learning journey. We offer fundamental to advanced level training, with on-demand, live, and virtual options to suit your busy schedule. Certifications help you validate and prove your skill and expertise in Google Cloud technologies.
Manual Last Updated December 10, 2021
Lab Last Tested August 12, 2021
Copyright 2022 Google LLC All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.