**Google Cloud Vision offers developers an easy way to integrate vision detection capabilities into their applications**. These include image labeling, face and landmark detection, optical character recognition (OCR), and explicit content tagging, among others.

  

Authentication is an important step before automating processes with Google Cloud Vision. You can find step-by-step instructions for establishing a connection with your Google Vision instance in the [Google Vision authentication page](https://docs.uipath.com/integration-service/automation-cloud/latest/user-guide/uipath-google-vision-authentication).

  

The [Google Vision activities](https://docs.uipath.com/activities/docs/uipath-google-vision-activities) can be enabled in [UiPath Studio](https://www.uipath.com/developers/studio-download) using the connection, **allowing you to build automations that interact with your Google Vision data**. This helps you to perform create, read, update, and delete operations on your Google Vision objects within your automation workflows.

  

The UiPath connector for Google Vision is compatible with REST API v1. Further information can be found at the [Cloud Vision API documentation platform](https://cloud.google.com/vision/docs/reference/rest).

  

At the moment, the Google Vision connector **does not support events** and is currently in **preview**.

Integrates Google Vision features, including image labeling, face, logo, and landmark detection, optical character recognition (OCR), and detection of explicit content, into applications.

Experience the seamless Google Vision integrations of image labeling, face and landmark detection, optical character recognition (OCR), and explicit content tagging. Uncover the potential to effortlessly classify images into thousands of categories, detect individual objects and faces within images, and extract printed words with precision.

The UiPath Google Vision connector offers a gateway to the power of machine learning models encapsulated in a user-friendly REST API. Whether you're a developer seeking quick classification or an enthusiast exploring the depths of image understanding, UiPath's connector ensures a seamless and intuitive journey.

Enhance your applications with Google Vision integrations. Seamlessly benefit from capabilities like image labeling, face detection, OCR, and more.

Google Vision Integrations & Connector

Product Manager

This activity set is now on the official feed within UiPath Studio and is fully supported for Enterprise users.

  

This **UiPath Official package** includes the following activities:

  

**Google Vision Scope** \- Scope activity that will act as an authentication for each following Google Vision Activity.

**Annotate Image** - This will implement the generic Google Vision API call.

**Logo Detection** - The Activity will try to identify logos annotator on the specified image.

**Safe Search** \- The Activity will do a safe search analysis on the specified image identifying racy, adult, violent or medical content.

**Web Detection** - The activity will search the web for similar images and return full matching and partial matching urls which include the image.

**Label Detection** - The activity will extract the most relevant labels of the image. The labels are image characteristics.

**Text Detection** - The activity will extract the relevant text blocks along with their language and position.

**Face Detection** - The activity will crop faces from the specified image.

**Handwritten Text Detection** \- The activity will extract handwritten text along with its language and position. 

  

All activities are localized in Chinese, French, German, Japanese, Korean, Portuguese (Brazilian), Russian.

  

Documentation is located at https://docs.uipath.com/activities/docs/google-vision-about

Image analysis powered by Google's Vision service

これは Google Vision アクティビティパッケージのベータ版です。一部の機能は将来的に変更になる可能性があります。

次のアクティビティが含まれています。

**Google Vision スコープ** \- 各 Google Vision アクティビティの認証機能を担うスコープアクティビティ

**画像にアノテーションをつける** - 一般的な Google Vision API コールを実装

**ロゴを検出** - 指定された画像上のロゴを識別

**セーフサーチ** \- 指定された画像上で、アダルトコンテンツ、差別的コンテンツ、暴力コンテンツ、医学コンテンツを識別しでセーフサーチ分析を実行

**ウェブ検出** - ウェブで類似の画像を検索し、完全適合または部分適合している画像の URL を戻す

**ラベルを検出** - 画像の最も関連性の高いラベルを抽出 (ラベルは画像特性)

**テキストを検出** - 言語と位置の沿った関連するテキストブロックを抽出

**顔検出** - 指定された画像から顔を切り出す

**手書き文字認識** \- 言語と位置の沿った関連する手書きのテキストブロックを抽出 **\*\*NEW\*\***

**すべてのアクティビティは、日本語、フランス語、ロシア語でローカライズされています。**

アクティビティについて詳しくは、[こちら](https://integrations.uipath.com/lang-ja/docs/google-vision)をお読みください。

画像から関連する注釈を抽出するのに使用できる Google Vision アクティビティパッケージ

This activity set is now on the official feed within UiPath Studio and is fully supported for Enterprise users.

  

This **UiPath Official preview package** includes the following activities:

  

**Google Vision Scope** \- Scope activity that will act as an authentication for each following Google Vision Activity.

**Annotate Image** - This will implement the generic Google Vision API call.

**Logo Detection** - The Activity will try to identify logos annotator on the specified image.

**Safe Search** \- The Activity will do a safe search analysis on the specified image identifying racy, adult, violent or medical content.

**Web Detection** - The activity will search the web for similar images and return full matching and partial matching urls which include the image.

**Label Detection** - The activity will extract the most relevant labels of the image. The labels are image characteristics.

**Text Detection** - The activity will extract the relevant text blocks along with their language and position.

**Face Detection** - The activity will crop faces from the specified image.

**Handwritten Text Detection** \- The activity will extract handwritten text along with its language and position. 

  

All activities are localized in Chinese, French, German, Japanese, Korean, Portuguese (Brazilian), Russian.

  

Documentation is located at https://docs.uipath.com/activities/docs/google-vision-about

Introduction to Google Cloud Vision API
---------------------------------------

The Google Cloud Vision API empowers developers to comprehend the content of images through the encapsulation of robust machine learning models within a user-friendly REST API.

  

It swiftly categorizes images into an extensive array of classifications, e.g., "sailboat," "lion," or "Eiffel Tower." Additionally, it adeptly identifies individual objects and faces within images, and proficiently locates and interprets printed words embedded within the visual content.

### Initial Configuration for Using Google Vision Activities Package

Before using the the Google Vision Activities Package, you need to configure your applications using the [Google Cloud Platform](https://console.cloud.google.com/) .

  

There are two configuration steps:

1.  **Enable APIs** - this step enables automation by granting API access to your Google applications.
2.  **Create Credentials** - this specifies the authentication type used to interact with your enabled APIs.

Activities in the Google Vision Activities Package
--------------------------------------------------

The activities included in this package are:

*   [Google Vision Scope](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-scope) - Handles the authentication to the Google Vision service.
*   [Annotate Image](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-annotate-image) - Requests one or more annotation types per image.
*   [Face Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-face-detection) - Detects multiple faces within an image, along with the associated key facial attributes like emotional state or wearing head wear. Facial Recognition is not supported.
*   [Handwriting Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-handwriting-detection) - Identifies and reads handwritten text inside the image.
*   [Label Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-label-detection) - Detects broad sets of categories within an image, ranging from modes of transportation to animals.
*   [Logo Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-logo-detection) - Detects popular product logos within an image.
*   [Safe Search](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-safe-search) - Detects explicit content like adult content or violent content within an image.
*   [Text Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-text-detection) - Detects and extracts text within an image, with support for a broad range of languages, along with support for automatic language identification.
*   [Web Detection](https://docs.uipath.com/activities/other/latest/legacy-integrations/google-vision-web-detection) - Searches the internet for similar images.

Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy-to-use REST API.

RPA Solution Architect

Typing the text from the MRZ of identification cards can be tedious. With the MRZ extractor this becomes much simpler. With the help of Google Vision this activity can extract the text within the MRZ zone of identification cards. Besides the extraction this activity can also parse the MRZ text using a self build parser. This parser extracts the information which is encoded in the MRZ text and labels each portion of it.

As inputs you need to provide an image of the ID from which you would like to extract the MRZ text and a .json file containing your credentials for use of the Google Vision API. Afterwards the text extracted from the image can be found in the TextResult block. The ParseMRZ option can be set to either True or False (default: False). When set to true the ParserResult block will yield the parsed MRZ code.

An activity that allows the user to extract text in the MRZ of identification cards. It also allows for parsing of the extracted MRZ text. This however is still a prototype parser.

Google Cloud Vision 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.

  

The Google Vision package can perform metadata analysis on images. There are multiple use cases depending on the industry and application.

Google Cloud Vision allows developers to easily integrate vision detection features within applications.

UiPath Solution Architect

The activity requires the following arguments:

  

1\. **in\_str\_Output\_Folder** : Folder where the user wants the text files to be placed.

2\. **in\_str\_Api\_Key** : The Google Vision API Key.

3\. **in\_str\_BagOfWords\_File\_Path** : The path to the Text file which can be used as a DataBank for incorrect words.

4\. **in\_str\_Api\_ServiceKey\_Path** : The path to the Google vision JSON.

5\. **in\_str\_Input\_Folder**: The folder where the images (\*.jpeg,\*.PNG) are placed.

  

  

**To learn how to get the Google API key and JSON file for free you can refer to my blog post:**

**https://www.kartikaydhar.online/post/handwriting-recognition-bot-uipath-ai**

Use this Bot to read text in images (like handwritten notes) and create a DataBank that can be used for future runs to make the recognition more robust and quick. This activity requires Google Vision API.

Google Cloud Vision enables integration of advanced vision detection capabilities into applications. Features include image labeling, face and landmark recognition, optical character recognition (OCR) and content categorization, making it a versatile tool for developers.

The UiPath connector for Google Cloud Vision facilitates easy access to powerful machine learning models through a user-friendly REST API. It swiftly categorizes images across numerous categories (e.g., "sailboat", "lion", "Eiffel Tower"), identifies objects and faces and extracts printed text from images.

### How It Works

To initiate outbound automation between UiPath and Google Vision, the connector establishes secure, authenticated connections.

Refer to the [Authentication Guide](https://docs.uipath.com/integrations/docs/uipath-google-vision) in the connector documentation before embarking on your project to ensure the integration.

### Activities

- [Annotate File](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-annotate-file) - Annotates a file.
- [Face Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-face-detection) - Detects faces using Google Vision.
- [Handwriting Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-handwriting-detection) - Detects handwriting using Google Vision.
- [Label Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-label-detection) - Detects labels using Google Vision.
- [Logo Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-logo-detection) - Detects logos using Google Vision.
- [Text Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-text-detection) - Detects text using Google Vision.
- [Web Detection](https://docs.uipath.com/activities/other/latest/integration-service/uipath-google-vision-web-detection) - Detects webpages using Google Vision.

Google Cloud Vision integrates advanced image detection features like labeling, face recognition, and OCR. The UiPath connector simplifies access via a REST API.

	Listing	Apps	Downloads
	Google Vision Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy-to-use REST API.		13054
	Ciphix - MRZ Reader Google Vision An activity that allows the user to extract text in the MRZ of identification cards. It also allows for parsing of the extracted MRZ text. This however is still a prototype parser.		566
	Google Vision Google Cloud Vision allows developers to easily integrate vision detection features within applications.		<100
	Handwriting Recognition Use this Bot to read text in images (like handwritten notes) and create a DataBank that can be used for future runs to make the recognition more robust and quick. This activity requires Google Vision API.		<100
	Google Vision Activity Package Google Cloud Vision integrates advanced image detection features like labeling, face recognition, and OCR. The UiPath connector simplifies access via a REST API.		<100

Visual Content Made Easy with Google Vision Integrations and Connector

Google Vision connector

Explore Studio Desktop listings

Similar apps

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence