fix: layout coordinate scaling and OCR table extraction (#582)#593
Merged
fix: layout coordinate scaling and OCR table extraction (#582)#593
Conversation
github-project-automation
bot
moved this from In Review
to Done
in Kreuzberg Open-Source Kanban
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
fixes #582 and relates to #574. Scanned and image-based PDFs were returning
0tables and assigningpage_number: 1to all OCR elements.This PR addresses three distinct bugs:
ocr.rs): Scaled layout detections (from 640×640) up to the OCR render resolution (e.g., 2480×3508) before running TATR table recognition or generating layout hints. This restores word intersection matching.ocr.rs): Stampedelem.page_number = page_idx + 1directly on each OCR element rather than accepting the Tesseract default of1.mod.rs): Moved layout detection upfront so thepaddle-ocr/pipeline execution path doesn't silently skip layout detection entirely.