I cannot for the life of me find which of these OCR engines are free and which are not. I’m seeing different answers being marked as correct here on the forum, and I cannot find any official UiPath documentation that explicitly lays out which are free and which aren’t.
Is Tesseract free? (I think so…)
Is Microsoft OCR free? (I think so…)
Is Microsoft Azure OCR free? (Not sure, but I think it is…)
Is Omnipage OCR? (Not sure, but I don’t think so…)
Tesseract OCR and Omni Page OCR are free. For aomni Page OCR you need to install the package UiPath.OmniPage.Activities.
OCR engine is 2 types : Local and Cloud.
Local based OCR engine such as MicrosoftOCR, Tesseract or OminPage is free in UiPath environment.
On the other hands, Cloud OCR such as Azure Computer Vision, Google Computer Vision or UiPath Document OCR for digitize purpose basically requires fee except under certain conditions.
For example, in Azure Computer Vision there is free plan and we can use it within 5000 transaction per month.
Microsoft Azure Computer Vision
Google Cloud Vision: we can use it with no charge in first 1000 units per month.
Or we can use UiPath DocumentOCR for free in Community Plan.
Hope this helps you.
Thanks, @Yoichi and @vrdabberu .
This doesn’t seem as straightforward as “free/not free” as UiPath would have it seem.
EDIT: Found this buried in the “Best Practices Guide_DUPT.pdf” in the Academy training:
“Try different OCRs and see which gives the best results. Start with UiPath OCR and if the results are not as good as needed:
• Google / Microsoft OCRs (these require an extra license bought from them)
• UiPath CJK (for Chinese, Japanese, Korean)
in order to add more information and ask for your help for a similar issue.
- With UiPath studio community edition I use the “UiPath Document OCR” in order to read image on Goggle Chrome in order to apply some logic in the number that are extracted, however there is a max to the call to the OCR that is 50call in 1h.
This limit can be solved only with the purchase of the enterpise edition? There are some workarounds or other OCR without limits? I tried the tesseract ocr but it seems doesn’t working.
This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.