We were founded in 2005 in a tiny apartment in Bucharest, Romania as DeskOver.

Fittingly, it was a customer who, in 2012, first saw the immense possibilities for us in the fledgling RPA market. Our desktop automation product launched in 2013. In 2015, we introduced our enterprise platform along with our new name.

Today, UiPath is the fastest-growing enterprise software company in history with scores of offices, thousands of employees, partnerships with the world’s best consulting and BPO firms, a 500,000-strong developer community, and 5MM+ robots at work in over 5,000 global enterprises.

Our mission is to deliver the leading Robotic Process Automation platform to our clients for an automation first mindset.

We build software robots that automate repetitive processes. Our software robots take on the tedious, mind-numbing work and free people to do the more stimulating, creative work worth doing.

But no matter how much we’ve grown, one thing hasn’t changed. We’re still building a company we love to work for

This activity set is now on the official feed within UiPath Studio and is fully supported for Enterprise users. It consists of 8 activities usable within a common scope activity:

Microsoft Vision Scope - Scope activity that will act as an authentication for each following Microsoft Vision activities.

Detect Faces - The activity will detect all the faces from the image and give information of the persons gender and age.

Generate Description - The activity will generate a natural language description for the image.

Safe Search - The activity will do a safe search analysis on the specified image, identifying adult or racy content.

Generate Tags - The activity will extract the most relevant tags from the image. The tags are image characteristics.

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

Get Color - The activity will get the dominant colors from the image.

Get Thumbnail - The activity will crop the most relevant part of an image.

Read Handwritten Text - The activity will read handwritten or printed text.

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

Click here for the documentation of the activities. 

Image analysis powered by Microsoft's Computer Vision service

共通のスコープアクティビティ内で利用できる次のアクティビティが含まれています。

Microsoft Vision スコープ - 各 Microsoft 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

顔を検出 - 画像に含まれる複数の顔を検出し、年齢と性別を取得

説明文を生成 - 画像についての説明を自然言語で生成

セーフサーチ - 指定された画像上のアダルトコンテンツや差別的コンテンツを識別しでセーフサーチ分析を実行

タグを生成 - 画像から最も関連するタグを抽出 (タグは画像特性)

テキストを読み込み - 言語と位置の沿った関連するテキストブロックを抽出

配色を取得 - 画像から多く利用されている色を取得

サムネイルを取得 - 画像で最も意味のある部分を切り取り

手書きのテキストを読み込み - 手書きまたは印刷されたテキストを読み取り

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、こちらをお読みください:

https://integrations.uipath.com/lang-ja/docs/microsoft-vision 

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

Technology Manager

Hi!!I have created a Face To Face Verify using Microsoft Vision, I would be glad if i can contribute to your custom activity, dude!! Regards,Julio.

Hi. I am currently exploring MS Vision Detect Face Activity. It returns output as below :FaceImage[1]{FaceImage{Age=34,Gender=“Male”,Position=[{X=56,Y=169,Width=225,Height=225}]}}But, this is unique variable type as faceimage[], So I am facing Issue that I cannot extract specific value from this output like "34". If you can suggest solution, that would be helpful. Thank you!

hi team,'Main': The private implementation of activity '1: Main' has the following validation error:&nbsp;&nbsp;The activity author supplied RuntimeArgument named 'Result' must be bound to the argument returned by the activity's Result property.Exception Type: System.Activities.InvalidWorkflowExceptionRemoteException wrapping System.Activities.InvalidWorkflowException: The following errors were encountered while processing the workflow tree:please help me. im stuck here.

I am exploring this and it is good. Generate Description is very useful. Also read handwrittne text is very useful. Unfortunately - MicrosoftAzureComputerVisionOCR activity only works for trial key. When I gave the proper subscription key after creating the service in azure - it is failing. Do note same subscription key works for Microsoft Vision Scope and Read Handwritten text or any other Vision Services from MS.   Request you to pls check. 

Robots can read handwriting! - There's a lot in here, but the handwritten text detection is something extraordinary. In some of the tests we ran, the robots could read messy handwriting even better than the humans could!


Microsoft vision_Free access - If there would free access such as Service URL and API key for some extent then I would be helpful to understand the features of it


Very Useful Component - This will be helpful when organizing pictures/images based on tags.


- Updated to use the latest version of Microsoft Vision API (SDK version 6.0.0).

Localized in Chinese, French, German, Japanese, Korean, Portuguese (Brazilian), Russian.

Microsoft Vision

Microsoft Vision

Help

How To