Skip to content

Commit

Permalink
Update instructions for adapting bottlecap map
Browse files Browse the repository at this point in the history
  • Loading branch information
daniel-jakob committed Jan 15, 2024
1 parent b7dbaba commit e1d7b44
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ pip install -r requirements.txt
### If looking to adapt for your own bottlecap map...
You must take a photo of your map, ideally as similar as possible to the one I used (found in `germany_beer_map/data/images/map.jpg`). I suggest a high contrast background. Replace the aforementined file with your picture. Find a reference outline image of your country online and replace the `map_ref.jpg` file. Change the `None` `circles = detect_circles(...)` line in `main.py`
You must take a photo of your map, ideally as similar as possible to the one I used (found in `germany_beer_map/data/images/map.jpg`). I suggest a high contrast background. Replace the aforementined file with your picture. Find a reference outline image of your country online and replace the `map_ref.jpg` file. Change the `None` in `picture_out_filename=None` in the `circles = detect_circles(...)` line in `main.py` to a chosen filename. Run the script and see if all of the circular hole cutouts of your map are detected. If not, play around with the `minRadius=...` and `maxRadius=...` parameters in `cv2.HoughCircles(...)` in the `src/image_processing/circle_detection.py` file. Once all circles are being detected, ensure that the outlines (contours) of both the photograph and reference image are being detected correctly, the detected outline can be outputted to an image file in a similar fashion to the circle detection, except for the `detect_outline(...)` lines.
## Testing
Expand Down

0 comments on commit e1d7b44

Please sign in to comment.