Skin redness
Redness (a* proxy)
How much redder the cheeks and nose are than the forehead, read on the CIE a* (red–green) axis from uncalibrated sRGB.
Also searched as facial redness, red skin and rosacea-type redness.
How to read it
the cheeks and nose read no redder than the forehead on the a* axis.
the cheeks and nose read a little redder than the forehead.
the cheeks and nose read markedly redder than the forehead on the a* axis.
Uncalibrated sRGB from a phone is not colorimetry. Melanin and haemoglobin absorb in overlapping bands, so at deeper skin tones a* is dominated by melanin and this value stops being a redness measure at all. The app says so when that applies.
Why every value has an error bar
Every value Canthion reports carries a 1σ uncertainty propagated from MediaPipe Face Mesh's published accuracy (3.96% of inter-ocular distance mean absolute error per landmark, Kartynnik 2019). On a typical photo with 300 px between the pupils, that is about 12 px of wander on every point. Small ratios and angles inherit it, so their intervals are wide. A number without an interval is a number pretending to be more precise than it is.
Common questions
What is skin redness?
How much redder the cheeks and nose are than the forehead, read on the CIE a* (red–green) axis from uncalibrated sRGB. Positive difference = cheeks/nose redder than forehead.
How is skin redness measured from a photo?
From the pixels of the photograph, not from landmarks: the region (cheeks + nose vs forehead) is converted to CIE L*a*b* and the value is read as a statistic of those pixels. Because it depends on lighting, it is reported relative to the rest of the same photograph and marked lighting-dependent.
How reliable is skin redness from a photograph?
Uncalibrated sRGB from a phone is not colorimetry. Melanin and haemoglobin absorb in overlapping bands, so at deeper skin tones a* is dominated by melanin and this value stops being a redness measure at all. The app says so when that applies.
Related measurements
The rest of the skin set, then the nearest measurements elsewhere on the face. Every one is computed on the same photograph, in the same run, with its own error bar.
Also: how bone-level measurements are taken from a photo · methodology · glossary · all 35 insight pages