Why Phone Photos Lie About Centering (And How Homography Fixes It)
How a 5° hand tilt distorts your card's border ratio by up to 8% — and the projective geometry that straightens it out.
Bite-sized engineering deep dives into projective geometry, subpixel signal processing, and how we measure a card from a photo.
Explore the full 4-minute brief on subpixel profiling, directional filters, and how the estimates score on held-out graded slabs.
How a 5° hand tilt distorts your card's border ratio by up to 8% — and the projective geometry that straightens it out.
Why standard computer vision sees thousands of fake scratches in card glitter — and how directional filter banks extract real defects.
How parabolic interpolation on Gaussian edge profiles turns discrete camera pixels into micron-level metrology.
Why 1980s consensus algorithms produce wobbly card boundaries, and how modern marginalization achieves rock-solid subpixel alignment.
How dichromatic reflection decomposition stops bright lighting hotspots from masquerading as card damage.
Why a PSA 10 can fail at Beckett, why CGC 9s cross to PSA 10s, and what 14,900+ slabs reveal about centering and surface thresholds.