Change theme
Help
Press space for more information.
Show links for this issue (Shortcut: i, l)
Copy issue ID
Previous Issue (Shortcut: k)
Next Issue (Shortcut: j)
Sign in to use full features.
Vote: I am impacted
Notification menu
Refresh (Shortcut: Shift+r)
Go home (Shortcut: u)
Pending code changes (auto-populated)
View issue level access limits(Press Alt + Right arrow for more information)
Request for new functionality
View staffing
Description
Description : There is an issue with the Vision API where the text returned by the OCR engine is to be properly aligned with the actual text locations on the PDF, instead of being slightly offset.
Problem you have encountered: The product depends extremely heavily on correct OCR alignment for being able to tell exactly where on the page the text is located. This means that if the OCR text is misaligned from the actual text, we are unable to properly locate the text on the page to work with it.
What you would like to accomplish: The OCR data should be correctly aligned with the text instead of being slightly offset.
Other information :
Resource Name(s) : Vision API
API URL/Method :https://vision.googleapis.com/v1/files:asyncBatchAnnotate
API Version : v1
Source of the requests : PowerShell, following thishttps://cloud.google.com/vision/docs/pdf
Request to Assignee : Could you please help in correctly aligning the OCR data and steps to achieve proper alignment?
Found related documentation :https://cloud.google.com/vision/docs/file-small-batch https://cloud.google.com/vision/docs/ocr https://cloud.google.com/vision/docs/pdf#powershell https://cloud.google.com/functions/docs/tutorials/ocr
[1]
[2]
[3]
[4]