Cloud Vision documentation | Cloud Vision API

Cloud Vision 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.

Set up the Vision API
Quickstarts: Using client libraries or API explorer
Detect text in images
Detect text in files (PDF/TIFF)
Detect handwriting in images
Detect faces

Training and tutorials

Tutorial

OCR tutorial

Learn how to perform optical character recognition (OCR) on Google Cloud Platform. This tutorial demonstrates how to upload image files to Google Cloud Storage, extract text from the images using the Google Cloud Vision API, translate the text using the Google Cloud Translation API, and save your translations back to Cloud Storage.

Walkthrough

Create a simple Hello, World! function in the console

Quickly deploy your first function without any local setup.

Training

Big data and ML fundamentals

This one-day instructor-led class introduces participants to the big data and machine learning capabilities of Google Cloud. It provides a quick overview of Google Cloud and a deeper dive into the data processing capabilities.

Tutorial

Detect text in images by connecting Functions, Storage, Vision API, Pub/Sub, and the Translation API

React to Cloud Storage changes with a function that processes an image using the Vision API to extract text and then pass it to other services.

Codelab

Automated Classification of Data Uploaded to Cloud Storage with the DLP API and Cloud Functions

Automatically classify data uploaded to Cloud Storage using Pub/Sub, Cloud Functions, and the Data Loss Prevention API.

Use cases

Use case

Deploying a serverless integration solution based on Cloud Functions and Pub/Sub

Shows how to set up and test a data integration solution.

Functions Pub/Sub Serverless

Use case

System testing Cloud Functions using Cloud Build and Terraform

Describes how to automate end-to-end testing of an app built with Cloud Functions.

Cloud Build Terraform Automation

Use case

Streaming data from Cloud Storage into BigQuery using Cloud Functions

Demonstrates how to stream new objects from a Cloud Storage bucket into BigQuery by using Cloud Functions.

Storage BigQuery Import

Use case

Processing User-Generated Content Using the Video Intelligence and Cloud Vision APIs

Shows how to deploy a set of Cloud Functions in order to process images and videos with the Cloud Vision API and Cloud Video Intelligence API.

Video Intelligence Cloud Vision Images

Code samples

Workflow

Streaming data from Cloud Storage into BigQuery using Cloud Functions

Learn how to stream new objects from a Cloud Storage bucket into BigQuery by using Cloud Functions.

Python

Workflow

Annotating multiple images in a single request and storing output in Cloud Storage

Run offline (asynchronous) detection services and annotation of a large batch of image files using any Vision feature type.

Java Node.js Python Ruby

Workflow

Setting a storage and processing location for OCR requests

Set a specific region to store and process resources used for an Optical Character Recognition (OCR) request.

C# Go Java Node.js PHP Python Ruby

Solution

Detecting and blurring offensive image content

Demonstrates using the Google Cloud Vision API and ImageMagick to detect and blur offensive images that get uploaded to a Cloud Storage bucket.

Node.js Python Go Java

Solution

Translating and speaking text from a photo with glossaries (Advanced)

Use Vision API, Translation API, Text-to-Speech API to detect text in an image, personalize translations, and generate synthetic speech from the translated text.

Python

Solution

Detect text in an image (OCR) and draw a border around the found text

Use Vision API to identify text in an image, and then annotate an image based on the text that is detected.

Python

Guides

Reference

Resources

Training and tutorials

Use cases

Code samples

Videos