Detect near-horizontal and near-vertical text
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12
- Forks
- 2
- Avg merge
- 13h 21m
- Merged PRs (30d)
- 98
Description
If text is within a few degrees (maybe 5°?) of being exactly horizontal or vertical, EasyOCR gives it a bounding box that's aligned with the image axis, not the text. This makes sense for most OCR users, but it's bad for me since those few degrees can create drift over the course of an entire image and produce intersections in the wrong spot.
Maybe EasyOCR has a parameter that can be used to tweak this behavior.
p444 and p507 for New Orleans 1951 Volume 5 may be examples of this.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the behavior described for p444 and p507 in New Orleans 1951 Volume 5, then inspect how the project invokes EasyOCR and whether its rotation or bounding-box options are exposed. Done should mean near-horizontal or near-vertical text can preserve its slight rotation, or that this behavior can be configured without causing drift.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 39/100