Assigned
Status Update
No update yet.
Comments
gu...@google.com
I have informed our engineering team of this feature request. There is currently no ETA for its implementation.
A current workaround would be to check the returned "boundingPoly" [1] "vertices" for the returned "textAnnotations". If the calculated rectangle's heights > widths, than your image is sideways.
[1]https://cloud.google.com/vision/reference/rest/v1/images/annotate#boundingpoly
A current workaround would be to check the returned "boundingPoly" [1] "vertices" for the returned "textAnnotations". If the calculated rectangle's heights > widths, than your image is sideways.
[1]
go...@gmail.com
I also need this problem solved :)
gu...@google.com
ji...@gmail.com
same :D
gu...@gmail.com
+1
Description
What you would like to accomplish:
dentity the font family, size of the font & the font color to simulate a text layer for the original document being read by Document Understanding AI
How this might work:
After API is finished analyzing document (PDF, GIF, TIFF), API would give a response similar to the following:
{
text-font-family: "Times New Roman",
text-font-size: "12",
text-font-color: "black"
}
Other information (workarounds you have tried, documentation consulted, etc):
Workaround: implement another Machine learning model to detect font family, font size & font color. Implementation of requested feature would be faster and would reduce customer pain.