How to use the Intelligent OCR for any PDF(other than invoice ) ? Both by Regex and Machine Learning Extractor?

How to use the Intelligent OCR for any PDF(other than invoice ) ? Both by Regex and Machine Learning Extractor and also using Flexicapture for Data Extractor? Can any one please help with the step by step process or has a demo .

Hi @Upasana_Datta

I just upload a tutorial step by step about Intelligent OCR using Position Based data extraction (now its named Form Extractor). Works really good in predefined forms, even if you have multiple pages.

The tutorial includes also how to configure your input form in your solution using Form Extractor activity.

Just let me know if you have another question.

Kind regards,

Andres

Hi Andreas,

Thank you so much for the help. In your video to extract the data Form Extractor was used which I was unable to find . Please let me know what to do next .

UiPath Version :- 19.10.4

Intelligent OCR ----> V4.0.1 (Highest version I could see)

Thank you once again for your help.

Thanks and Regards

Upasana

Hi @Upasana_Datta

That activity is only available on preview packages of Intelligent OCR, you can force to install the preview version of the packages editing the project.json file adding the following dependency “UiPath.IntelligentOCR.Activities”: “[4.3.0-preview]”,

Here (about-the-projectjson-file) you can find more ifnormation about how to edit the json file

Regards,

Andres

Thanks.Trying it out .

Thank you for all the Help…Facing another issue while exporting the result…with this error message.

Can you please help resolve this error. Thank you

Thank you for all the Help…Facing another issue while exporting the result…with this error message.

Can you please resolve this issue.

Works well except for table extraction, where I have found it is not fiddly to use and not reliable on pdf tables. Currently having to use other methods to extract table information.