Midface ratio
Eye–mouth distance : face length (Pallett)
The distance from the eyes down to the mouth, as a share of face length from hairline to chin. It is the only "midface ratio" with an empirical basis: Pallett, Link & Lee (2010) found raters preferred ≈0.36.
Also searched as eye to mouth distance, long midface, short midface and compact midface.
Depends on the user-placed hairline (trichion): no detector locates it, and it moves with hairstyle.
Measure yours →How to read it
the eye-to-mouth distance is short relative to face length (a compact midface).
this proportion sits near the value Pallett et al. identified as the preferred/average configuration.
the eye-to-mouth distance is long relative to face length (a long midface). Note the value depends on the user-placed hairline.
Every consumer app computes a different thing and calls it "midface ratio". This is the one definition with a citation, and it was derived on one population and one sex.
Reference values by population
| Reference population | Female (mean ± SD) | Male (mean ± SD) | n | Source |
|---|---|---|---|---|
| North American White | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| East Asian | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| South Asian | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| African / African diaspora | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| Middle Eastern | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| Hispanic / Latino | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. prov. |
| Not specified — show pooled | 0.36 ± 0.03 | 0.36 ± 0.03 | — | Pallett et al. 2010 — preferred value on Caucasian female faces (n=4 experiments); treated as the population-average configuration. Provisional for other groups. 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). 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.
References
- Pallett, Link & Lee (2010). New "golden" ratios for facial beauty. Vision Res 50(2):149–154. doi.org/10.1016/j.visres.2009.11.003
Common questions
What is midface ratio?
The distance from the eyes down to the mouth, as a share of face length from hairline to chin. It is the only "midface ratio" with an empirical basis: Pallett, Link & Lee (2010) found raters preferred ≈0.36. Derived on Caucasian female faces only; the authors read it as an averageness effect.
How is midface ratio measured from a photo?
It is computed from the face-mesh landmarks (iris_R, iris_L, sto, tr, me): dist(eyeLine, sto) / dist(tr, me). Every value carries a 1σ error bar propagated from the landmark detector's published accuracy, with a floor of ± 0.02, so a small difference inside the interval is not a difference.
What is a normal midface ratio?
Across the reference populations the anatomical norm is the same: 0.36 ± 0.03 for women, 0.36 ± 0.03 for men. This value is provisional and awaits line-by-line audit against the primary tables. Your own value is placed on the distribution you choose, as a percentile with its error bar.
What does a low or high midface ratio mean?
Below the mean: the eye-to-mouth distance is short relative to face length (a compact midface). Above the mean: the eye-to-mouth distance is long relative to face length (a long midface). Note the value depends on the user-placed hairline.
How reliable is midface ratio from a photograph?
Every consumer app computes a different thing and calls it "midface ratio". This is the one definition with a citation, and it was derived on one population and one sex.
This is the vertical optimum raters preferred in Pallett 2010, which is not 1.618 or anything derived from it.
Related measurements
The rest of the whole face 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