README: drop the "Known issues" section

Map screenshot reading (grid + unit detection) is working noticeably
better now; not sure exactly which of the recent fixes did it, but the
blanket "unreliable/fails often" caveat is no longer accurate enough
to keep. TODO.md still has the fuller fixed/open list.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Dominik Moritz Roth 2026-08-11 20:49:19 +02:00
parent 23615a8c92
commit 4556da37ff

View File

@ -48,11 +48,6 @@ Regression coverage for every intel-text format the OCR pipeline understands and
## Stack ## Stack
GTK4 + libadwaita (PyGObject) for the UI, Tesseract (via pytesseract) for OCR, Pillow/numpy for preprocessing, OpenCV for the map-table geometry (line detection, vanishing points, homography). Details on the coordinate system, OCR formats, solver internals, and how the map grid is recovered live in code comments (`solver.py`, `ocr.py`, `models.py`, `map_vision.py`) rather than here. GTK4 + libadwaita (PyGObject) for the UI, Tesseract (via pytesseract) for OCR, Pillow/numpy for preprocessing, OpenCV for the map-table geometry (line detection, vanishing points, homography). Details on the coordinate system, OCR formats, solver internals, and how the map grid is recovered live in code comments (`solver.py`, `ocr.py`, `models.py`, `map_vision.py`) rather than here.
## Known issues
- **Map screenshot reading is unreliable.** Grid detection and enemy/unit detection off a map screenshot both fail often: misread grids, missed or misclassified units, screenshots rejected as "not a map" when they were one. Screenshots the app gets wrong are now saved locally (see `debug_capture.py`) to develop the detection against. Still an open problem, not a quick fix.
See `TODO.md` for the fuller list, including what's already been fixed.
## FAQ ## FAQ
### Is this cheating? ### Is this cheating?