Assigned
Status Update
Comments
va...@google.com <va...@google.com>
nr...@google.com <nr...@google.com> #2
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]
ja...@gmail.com <ja...@gmail.com> #3
I also need this problem solved :)
ja...@gmail.com <ja...@gmail.com> #4
same :D
ja...@gmail.com <ja...@gmail.com> #6
+1
ja...@gmail.com <ja...@gmail.com> #7
This needs more attention. It's not just a display issue as described in the report. The co-ordinates returned in 'boundingPoly' are incorrect if the image was taken on a phone. All the x points should be y and vice versa.
The workaround does not make sense as "boundingPoly" [1] "vertices" for "textAnnotations" does not indicate the image dimensions - it indicates the dimensions of the relevant text block inside the image.
The workaround does not make sense as "boundingPoly" [1] "vertices" for "textAnnotations" does not indicate the image dimensions - it indicates the dimensions of the relevant text block inside the image.
Description
The Cloud Vision API's image properties color recognition feature is incorrectly identifying the color of certain images. Specifically, the API returns a color value of white with a high score (e.g.:
0.8
) and a significant pixel fraction (e.g.:0.3
), despite the images clearly not being predominantly white. The affected images, which predominantly feature brown and orange hues, are attached for reference.Normally, the API performs well, but this issue seems to occur exclusively with images containing brown and orange colors, where it inaccurately identifies these as white.
Could you please investigate this issue? Let me know if additional details or examples are needed.