Hi,
I am trying to extract details (Name, Age, Profession, Salary, and Denomination) from multiple images attached below through Google AI Studio then paste it in Excel file. May I know what can be the efficient step by step process and what are the UiPath activities that can be used? I am using REFramework as well.
Kindly see attached images below that will be extracted:
Sample Output Excel Extraction:
Thank you.
Best regards,
Robert
hi, @RobertRussell_Monsalud put all your images in one folder. use Directory.GetFiles to list all the image paths. Loop over them with a For Each. For every image path, feed it into the Google Cloud Vision OCR activity. You get only raw text-easy.
Now, pull out details with Regex, like grab “Name:”, “Age:”, “Profession:”, “Salary:” and scan lines for Denomination numbers. Dump every result in a DataTable (just basic Add Data Row activity). When the loop’s done, Write Range in Excel.
REFramework-wise, do all image reading inside ‘Process’ state, handle exceptions just like normal.
Hi @arjun.shiroya, may I know what will be the dependency for Google Cloud Vision OCR? Thank you.
You just need the UiPath.UIAutomation.Activities package for Google Cloud Vision OCR—it’s already built in
Can you kindly elaborate it more? Thank you.
UiPath Google Cloud Vision OCR activity: It’s part of the UiPath.UIAutomation.Activities package, so just keep this package updated in your project.
You’ll need a Google Cloud API key from your Google Cloud Platform account. This key lets UiPath connect securely to Google Vision services.
Double check the raw OCR output first - write it to a text file and see what Google Vision spits out.
Adjust your Regex or string methods to match exactly how that text looks. Copy-paste the exact text lines and build patterns for “Name: .”, “Age: .” etc
Log the parsing outputs one by one before you fill the DataTable, to catch what’s missing.
