Repository navigation
docs: research Vision page inspection APIs - #19
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Problem
Vision exposes geometry and similarity evidence, not semantic page decisions. A future implementation could read a document boundary's
topLeftlabel as reading orientation, or treat a small feature-print distance as a duplicate verdict.For example, a generated invoice whose number changed from
1048to1049had a feature-print distance of0.014, and a 180-degree-rotated page produced the same detected boundary corners. Treating either result as an automatic action could rotate, skip, or delete a distinct page.Changes
Adds one note for each request, covering availability, legacy and modern APIs, result shape, limits, source links, and follow-up characterization. The notes record the raw local measurements with their Xcode, SDK, macOS, architecture, revision, and crop-mode context.
The documented adoption boundary is inspection-only: future commands can report raw horizon, document-boundary, or similarity evidence, but need a separate product decision and behavior coverage before changing OCR, document recognition, or searchable-PDF behavior.