Demo of target-analyzer, photo-based scoring of paper targets, from this case study. Synthetic targets and readings. On the held-out target, cv_blob and yolo at 0.10 and 0.25 are matched to the real measured run; every other number is illustrative.

target-analyzer

demo range

2026-07-02 · shooter B · 10 m

readingproposedmatchedmissedspuriousoffset
cv_blob86420.59 mm
yolo ≥ 0.05108220.54 mm

move the threshold

yolo cut atproposedmatchedmissedspuriousoffset
yolo ≥ 0.05108220.54 mm
yolo ≥ 0.10 (the default)98210.54 mm
yolo ≥ 0.1598210.54 mm
yolo ≥ 0.2577300.48 mm
yolo ≥ 0.4055500.46 mm

A detector only proposes: a person confirms every target, so a spurious hole costs one click to remove and a missed one costs a click to place. Lowering the threshold trades misses for spurious holes. 0.10 is the default the real app ships with. Two readings are the same hole within 4 mm.

confirmed by a person

ring 10ring 8ring 10ring 9ring 9ring 10ring 8ring 9ring 7ring 8

the truth every reading is scored against

cv_blob

ring 10ring 10ring 9ring 10ring 9ring 8ring 1ring 2

classic blob detection, no threshold to move

yolo ≥ 0.05

ring 10ring 8ring 9ring 9ring 9ring 10ring 8ring 8ring 3ring 5

the trained detector, cut at the threshold chosen above