Switch to the v3.0 version of the Computer Vision analyze endpoint #255
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description of the Change
We recently updated from the v1.0 Computer Vision analyze endpoint to the v3.1 version. After further testing, I'm noticing less accurate image captions (which we store as alt text) are being returned, resulting in either lowering the confidence score fairly low (like ~30%) or you end up with no alt text ever being saved.
It seems the v3.0 endpoint is much more accurate, with most captions being in the >75% range. This results in more accurate alt text and more images that have alt text generated.
Alternate Designs
None
Benefits
More accurate image scanning results
Possible Drawbacks
None
Verification Process
I scanned multiple images with the v3.1 endpoint and then again with the v3.0 endpoint. Results across the board were much better with the v3.0 one.
Checklist: