AI Computer Vision is Now Available for Preview

Narasimha1 · February 20, 2019, 10:32am

I like this feature, very excited to use this…

nimin · February 20, 2019, 5:42pm

It’s an amazing feature. Congrats Team UiPath , Keep going…

Naveen_tg · February 20, 2019, 5:51pm

Finally

Lahiru.Fernando · February 21, 2019, 4:30am

Wow… I was waiting for this… Awesome work Team UiPath!!

renekramer · February 21, 2019, 10:56am

Thanks! Works for me!

Himanshu.joshi · February 21, 2019, 12:27pm

Great step by uipath.

waiting for the stable version.

Rashmi · February 21, 2019, 12:56pm

So finally, worked with Intelligent Activities Just now tried it … !!! love the way it works, smooth as same as Native application.

Waiting for more intelligent activities like open browser and all

SuperCool

satish.reddy1205 · February 21, 2019, 2:33pm

Can’t wait to use these in PROD

svillalobos · February 21, 2019, 5:28pm

After adding the Beta Feed.
Make sure to enable “Include Prerelease” when doing the package search.
Otherwise the package wont appear on the listing.

baisilgee · February 22, 2019, 3:59am

Hi @Ryan_Rush ,

First of all sorry for the late replay. presently I am capable of installing and go on with the awesome activity along with the superb features…

Thank you for your follow up and all.

Thanks and regards,

Baisil Geevarghese

sachin_sharma · February 22, 2019, 5:00am

there are many awesome feature i will try it:clap:

KevinS · February 22, 2019, 2:44pm

SUCCESS!!

I’ve tried the beta release and found it to be a big improvement in a previously difficult (but common) use case. Great job team. Here are the details:

I recently produced a demo video called, “Can a Robot Do My Taxes?” https://youtu.be/A-1b-693yiI

As an initial step, the automation reads PDF tax documents such as a W2, which have a dense plane of text in boxes with very small header type. I ran into the well known issue where Get Text and similar activities have difficulty recognizing a single data field within such a PDF. I had to try many different approaches before finding one that was suitable. Even then it was bulky with many additional activities required.

After this week’s announcement I loaded Computer Vision and was able to easily grab the single bits of text that I wanted from the W2 - no special config steps, no string manipulation required. Better yet, I ran other W2 examples through and it remained accurate without adjustment.

Again, great job! Can’t wait for this to go into production.

Kevin

Ryan_Rush · February 22, 2019, 3:00pm

Really excited to hear this! Thanks for letting me know.

Cosin · February 22, 2019, 4:53pm

thanks kevin! it’s awesome to hear new/unexpected ways this is useful

Not sure if you’ve tried a somewhat hidden feature: the box-selection for GetText. It can scrape a designated area relative to an anchor. Maybe you’ll find it useful

html12345 · February 22, 2019, 5:48pm

Thnks for the post

KevinS · February 25, 2019, 2:10pm

Thank you @Cosin for the tip. I don’t think I’m familiar with the box-selection feature. Is that part of the original Get Text activity or the new CV Get Text in Computer Vision? If there’s any documentation on this feature I’d be interested, thanks!

Cosin · March 1, 2019, 7:40pm

Part of the new CV set of activities.

To try it out, in the CV.getText, click indicate and do a box selection in the wizard, instead of clicking a word. After that you will need to pick an anchor for it. At runtime, it will scrape the whole area of the selection. Very similar to scrape-relative

Kadiyala_Venu_Madhav · February 27, 2019, 7:00am

thanks

Anas.Mohammed · February 28, 2019, 12:45pm

excellent

ImPratham45 · March 2, 2019, 9:14am

I am facing error while running CV activity in beta version

Please help me out to resolve this issue I am very excited to work with CV