Image Recognition using Ui. Vision

Hi, I am new to Ui. Vision and I need to automate some tasks such as Image Recognition and Voice Recognition.
I searched on the web but could not find any helpful one.

Can you please help me out here so that I can use Ui. Vision for Image recognition and Voice Recognition automation.

Please provide from ground 0 as I am new to this tool.

Thanks & Regards
Prateek Kaushik

Hi, what kind of tasks do you want to automate?

Thanks for your response.

I want to automate following tasks:

Face Match :
· Facial recognition to perform matching

Liveliness Check
· Dynamic OTP displayed on screen
· Face Structure
· Voice Recognition
· Background Noise Check
· Video thru Device Camera
· Static Risk Check

Document OCR
· ID Documents should extract Information and match needs to be done with Data entered by User

Digital Forensics
· Forensics need to be conducted on the Images/Documents to check authenticity

Please Let me know how many tasks mentioned above can be automated using Ui. Vision.

Thank you.

UI.Vision is RPA software. RPA = Robotic process automation. It uses image recognition, text recognition and Selenium IDE commands to automate tasks on our desktop and browser.

Document OCR
· ID Documents should extract Information and match needs to be done with Data entered by User

=> You can do this with UI.Vision’s screen scraping and/or the OCR API.

1 Like

Thank you for response.

So only Document OCR is possible with Ui.Vision?

What about Facial Recognition/Face Match and Digital Forensics?

Please let me know.

Thank you

You can use a 3rd party API in combination with UIVision to achieve what you want (Google Vision, Microsoft Cognitive, etc)

Hi, that means as per your response, I cannot do Image Recognition, Face Recognition and Voice Recognition with UiVision?

And is it necessary to use 3rd party API in combination with UiVision.
Can not I just use it without any 3rd party API and do my recognition stuff?

Please provide your valuable response.

Thank you

You can, you would use XRun to run a script to make the API call. UiVision doesn’t natively do that as it would be out of the scope of what it is. That’s what gives you the flexibility though to automate anything and use any API or service you need.