Insights · Lips · Measurement

Upper : lower vermilion height

Height of the upper lip vermilion (red lip) at the midline divided by the lower.

Confidence
Tier A · tight interval
Unit
ratio (dimensionless)
Landmarks
ls, sto_upper, sto_lower, li
CI floor
± 0.06
dist(ls, sto_upper) / dist(sto_lower, li)
Measure yours
Illustration · on your scan the same lines are drawn on your own photo

How to read it

Below the mean

the upper vermilion is thin relative to the lower. This is the commonest configuration in every reference group; the widely quoted 1:1.6 "ideal" would place the majority of humans below it by construction.

Near the mean

upper and lower vermilion heights are in the typical proportion for the reference group.

Above the mean

the upper vermilion is comparatively full relative to the lower.

Caveat

Lip fillers, lip-liner overdrawing and pursing all change this value; it is a poor biological signal in the selfie population.

Reference values by population

Reference populationFemale (mean ± SD)Male (mean ± SD)nSource
North American White0.842 ± 0.2060.848 ± 0.2072326Farkas 1994/2005 (NA White young adults) prov.
East Asian0.85 ± 0.1970.857 ± 0.188618Farkas 2005 (Chinese/Japanese/Vietnamese/Thai pooled); Jayaratne 2012 (Southern Chinese, n=103) prov.
South Asian0.9 ± 0.2020.905 ± 0.205210Farkas 2005 (Indian); Metgudmath 2022 prov.
African / African diaspora0.88 ± 0.1810.885 ± 0.185300Farkas 2005 (African-American, Zulu, Angolan) prov.
Middle Eastern0.842 ± 0.2060.85 ± 0.205348Farkas 2005 (Turkish, Iranian, Egyptian); Al-Sebaei 2015 (Saudi, n=168) prov.
Hispanic / Latino0.857 ± 0.1880.864 ± 0.192120Farkas 2005 (Mexican-American) prov.
Not specified — show pooled0.864 ± 0.2360.869 ± 0.2343922Unweighted pool of the six groups above prov.
Where these numbers come from

Transcribed from the cited anthropometric literature; SDs of ratios are propagated conservatively (independence assumed). Entries marked prov. await line-by-line audit against the primary tables — see the norm provenance note.

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). For a typical 300 px inter-pupil photo that is ≈12 px per landmark, which is why small ratios and angles get wide intervals. A number without an interval is a number pretending to be more precise than it is.

References

Related: how bone-level measurements are taken from a photo · methodology · all insights