Microsoft Computer Vision **offers state-of-the-art algorithms for analyzing images and retrieving information**. With this technology, it becomes possible to detect inappropriate content in images, identify faces, estimate colors, categorize content, and describe images using complete English sentences.

  

Moreover, Microsoft Computer Vision **can intelligently generate image thumbnails**, which can help optimize the display of large images.

  

To begin utilizing these capabilities, **establishing a connection with your Microsoft Vision instance is necessary** before automating any processes. Detailed step-by-step instructions are available on the .

  

You can use the connection to enable the  in  and build automations that interact with your Microsoft Vision data. These activities allow you to execute create, read, update, and delete operations on your Microsoft Vision objects.

  

The UiPath connector for Microsoft Vision is compatible with the REST API v3.2, which **ensures seamless integration with your existing infrastructure**.

  

 currently **does not support events** and is in **preview.**

Microsoft product using pre-built algorithms to process images and return information.

Discover the enhanced capabilities of Microsoft Computer Vision, a tool designed to refine visual content analysis. Benefit from features like content detection, face recognition, color estimation, and seamless image categorization. This cloud-based service takes image processing to the next level, providing valuable insights for a variety of applications.

Integrate these advanced visual analysis capabilities into your automation workflows effortlessly with the UiPath Microsoft Computer Vision connector. Improve the efficiency of your processes by leveraging the combined strengths of Microsoft Computer Vision and UiPath. Start exploring the practical advantages of precise visual analysis today.

Leverage the combined strengths of Microsoft Computer Vision and UiPath to improve your processes. Explore the practical benefits of precise visual analysis today.

Microsoft Computer Vision Integrations and Connector

Product Manager

The Microsoft Vision package provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content, or it can be used to find all the faces in an image. It also has other features like estimating dominant and accent colors, categorizing the content of images, and describing an image with complete English sentences. Additionally, it can intelligently generate image thumbnails for displaying large images effectively.

  

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

  

\- Microsoft Vision Scope: Provides authentication for all Microsoft Vision activities

\- Detect Faces: detects faces from an image and provides information on gender and age.

\- Generate Description: Generates a natural language description for the image.

\- Get Color: Gets the dominant colors from the image.

\- Get Thumbnail:  Crops the most relevant part of an image.

\- Generate Tags: Extracts the relevant tags from the image. The tags are image characteristics.

\- Read Handwritten Text: Reads handwritten or printed text.

\- Read Text: Extracts relevant text blocks along with their language and position.

\- Safe Search: Does a safe search analysis on the specified image, identifying adult or racy content.

  

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

Simplify automating processes that use Microsoft Vision by replacing UI operations with background API calls.

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

The Microsoft Vision package provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content, or it can be used to find all the faces in an image. It also has other features like estimating dominant and accent colors, categorizing the content of images, and describing an image with complete English sentences. Additionally, it can intelligently generate image thumbnails for displaying large images effectively.

  

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

  

\- Microsoft Vision Scope: Provides authentication for all Microsoft Vision activities

\- Detect Faces: detects faces from an image and provides information on gender and age.

\- Generate Description: Generates a natural language description for the image.

\- Get Color: Gets the dominant colors from the image.

\- Get Thumbnail:  Crops the most relevant part of an image.

\- Generate Tags: Extracts the relevant tags from the image. The tags are image characteristics.

\- Read Handwritten Text: Reads handwritten or printed text.

\- Read Text: Extracts relevant text blocks along with their language and position.

\- Safe Search: Does a safe search analysis on the specified image, identifying adult or racy content.

  

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

Introduction to Microsoft Computer Vision Package
-------------------------------------------------

The Microsoft Computer Vision package offers algorithms designed for image processing, delivering comprehensive information in various applications. Its capabilities encompass content analysis, face detection, color estimation, image categorization, and descriptive sentence generation. Moreover, it exhibits intelligent functionality by generating effective image thumbnails for optimal display of large images.

Capabilities of Microsoft Vision Package
----------------------------------------

The Microsoft Computer Vision package performs metadata analysis on images, catering to diverse use cases across industries and applications.

  

This UiPath Microsoft Computer Vision package includes the following activities:

*   [Microsoft Vision Scope](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-scope) - Handles the connection to the Microsoft Computer Vision API and provides a scope for all Microsoft Vision activities.
*   [Analyze Image](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-analyze-image) - Makes a generic image call.
*   [Detect Faces](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-detect-faces) - Identifies and retrieves faces inside the image and gives information on the gender and age of the identified persons.
*   [Generate Description](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-generate-description) - Describes, in human-readable language, what is seen in an image.
*   [Generate Tags](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-generate-tags) - Generates a list of tags for individual objects found within the specified image.
*   [Get Color](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-get-color) - Gets the dominant foreground and background colors, a list of dominant colors and specifies whether the image is black and white.
*   [Read Handwritten Text](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-read-handwritten-text) - Identifies and reads handwritten text within the image.
*   [Read Text](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-read-text) - Reads the text from the specified image and gives information on the positioning of the text inside the image.
*   [Safe Search](https://docs.uipath.com/activities/other/latest/legacy-integrations/microsoft-vision-safe-search) - Specifies whether the image contains Adult or Racy content.

Simplify automating processes that use Microsoft Computer Vision by replacing UI operations with background API calls.

Microsoft Computer Vision provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content or it can be used to find all the faces in an image. It also has other features like estimating dominant and accent colors, categorizing the content of images, and describing an image with complete English sentences. Additionally, it can intelligently generate image thumbnails for displaying large images effectively.

Microsoft's Computer Vision functionality with Azure's Cognitive Services.

Microsoft Vision leverages algorithms to analyze images and deliver insightful information. It can detect mature content, identify faces, estimate dominant and accent colors, categorize image content and generate detailed English descriptions of images. Moreover, it can intelligently create image thumbnails, optimizing the display of large images.

### How It Works

Enable outbound automation between UiPath and Microsoft Vision by establishing an authenticated connection using the UiPath Connector for Microsoft Vision. Before starting your project, follow the steps in the [Authentication Guide](https://docs.uipath.com/integrations/docs/uipath-microsoft-vision-authentication) provided in the connector documentation to ensure proper setup.

### Activities

- [Analyze Image](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-analyze-image) - Extracts a rich set of visual features based on the image content.
- [Describe Image](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-describe-image) - Generates a description of an image in human readable language with complete sentences.
- [Detect Objects](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-detect-objects) - Performs object detection on the specified image.
- [Get Area of Interest](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-get-area-of-interest) - Returns a bounding box around the most important area of the image.
- [Get Read Result](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-get-read-result) - Fetches a read result for an existing Microsoft Vision operation ID.
- [Get Thumbnail](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-get-thumbnail) - Generates a thumbnail image with the user-specified width and height. By default, the service analyzes the image, identifies the region of interest (ROI), and generates smart cropping coordinates based on the ROI.
- [OCR](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-o-c-r) - Detects text in an image and extracts the recognized characters into a machine-usable character stream.
- [Read Text](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-read-text) - Optimized for text-heavy images and multi-page, mixed language, and mixed type (print – seven languages and handwritten – English only) documents.
- [Tag Image](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-tag-image) - Generates a list of words, or tags, that are relevant to the content of the supplied image.
- [List All Records](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-list-all-records) - Lists all records in Microsoft Vision.
- [Insert Record](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-insert-record) - Inserts a new record in Microsoft Vision.
- [Get Record](https://docs.uipath.com/activities/other/latest/integration-service/uipath-microsoft-vision-get-record) - Retrieves a record in Microsoft Vision.

This activity package is compatible with **UiPath Studio versions 2023.10 and newer.**

Enhance image processing with Microsoft Vision's advanced algorithms. Integrate with UiPath to detect content, generate thumbnails and more.

**Business Problem**

The organization is looking for a solution to do an optical character recognition to read and validate the cheques instead of entering the info manually.

Second requirement of the process is to also validate whether the cheque is valid or not.

**Solution:**

i. To minimize the manual work and increase process efficiency, we propose verification and validation of Cheque through automation process. 

ii. The system will be capable of validating the cheque through some mandatory fields like Digital Signature, MICR, cheque number with the help of a repository.

iii. Also, the system will perform verification of Account number, Amount in words and digits, Payee information.

iv. At the end of the process, the system will generate a report in both scenarios.

v. The whole solution is implemented using Microsoft OCR Engine.

Solution to do an optical character recognition to read and validate the cheques instead of entering the info manually

	コンポーネント	アプリ	ダウンロード数
	Microsoft Computer Vision Simplify automating processes that use Microsoft Computer Vision by replacing UI operations with background API calls.		12442
	Microsoft Vision Microsoft's Computer Vision functionality with Azure's Cognitive Services.		<100
	Microsoft Vision Activity Package Enhance image processing with Microsoft Vision's advanced algorithms. Integrate with UiPath to detect content, generate thumbnails and more.		<100
	Xebia - Cheque Analyzing Solution Solution to do an optical character recognition to read and validate the cheques instead of entering the info manually		<100

Refine Image Processing with Microsoft Computer Vision Integrations and Connector

Microsoft Vision コネクタ

デスクトップ版 Studio のコンポーネントを見る

類似のアプリ

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence