Classical Machine Learning
Select the bright seed pixels
BOTIE
Examples, experiments and workspace controls
Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.
Try your own inputs
Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.
Context for this challenge
Compare the image with the cutoff. Flatten the mask only for counting, add its entries, and pack the mask and count into the result in that order.
Botie needs bright foreground positions in the seed-tray photograph and a count of selected pixels. Those are two related outputs with different meanings.
Compare every intensity strictly above the cutoff, retain the mask's arrangement and flatten a copy only to sum its selected entries.
Examples and results
- Tray intensities
10 20 10 20 220 30 10 200 20 - Foreground cutoff
100
- Required result
[ [ [ 0, 0, 0 ], [ 0, 1, 0 ], [ 0, 1, 0 ] ], 2 ]
- Tray intensities
5 10 15 20 - Foreground cutoff
100
- Required result
[ [ [ 0, 0 ], [ 0, 0 ] ], 0 ]
Try a fresh construction
This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.
Stuck? Inspect a worked construction
The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.
Assumptions and test precision
The first result is a mask; the second is a pixel count. A global brightness cutoff can fail under shadows or similar foreground and background intensities. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.
A small tray at a lower brightness cutoff
This check uses the pieces from “Keep the seed mask beside its pixel count”.
BOTIE
- Tray intensities
40 41 0 40 - Foreground cutoff
40
Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.
Build a construction in the workspace above first. This case will test those pieces.
Why does a count of two foreground pixels not necessarily mean two seeds, and why should the mask be kept even after counting?
Thresholding identifies pixels under a brightness rule. Object grouping requires additional spatial reasoning.
The first result is a mask; the second is a pixel count. A global brightness cutoff can fail under shadows or similar foreground and background intensities.
Work through the Python challenges →