Bizygomatic width : physiognomic face height
Widest facial width divided by full face height from hairline (trichion) to menton.
Depends on the user-placed hairline (trichion) — no detector locates it and it moves with hairstyle.
Measure yours →How to read it
the face is narrow relative to its full height for the reference group.
width relative to full face height sits close to the reference mean (~0.74–0.75 in most groups).
the face is wide relative to its full height for the reference group.
Depends on the user-placed hairline. Undefined for receding hairlines; not comparable across hairstyles.
Reference values by population
| Reference population | Female (mean ± SD) | Male (mean ± SD) | n | Source |
|---|---|---|---|---|
| North American White | 0.759 ± 0.042 | 0.744 ± 0.043 | 2326 | Farkas 1994/2005 (NA White young adults) prov. |
| East Asian | 0.782 ± 0.046 | 0.775 ± 0.044 | 618 | Farkas 2005 (Chinese/Japanese/Vietnamese/Thai pooled); Jayaratne 2012 (Southern Chinese, n=103) prov. |
| South Asian | 0.757 ± 0.046 | 0.747 ± 0.044 | 210 | Farkas 2005 (Indian); Metgudmath 2022 prov. |
| African / African diaspora | 0.75 ± 0.045 | 0.737 ± 0.044 | 300 | Farkas 2005 (African-American, Zulu, Angolan) prov. |
| Middle Eastern | 0.749 ± 0.042 | 0.738 ± 0.042 | 348 | Farkas 2005 (Turkish, Iranian, Egyptian); Al-Sebaei 2015 (Saudi, n=168) prov. |
| Hispanic / Latino | 0.771 ± 0.046 | 0.765 ± 0.045 | 120 | Farkas 2005 (Mexican-American) prov. |
| Not specified — show pooled | 0.761 ± 0.048 | 0.751 ± 0.047 | 3922 | Unweighted 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
- Farkas, Katic & Forrest (2005). International Anthropometric Study of Facial Morphology in Various Ethnic Groups/Races. J Craniofac Surg 16(4):615–646. doi.org/10.1097/01.SCS.0000171847.58031.9E
Related: how bone-level measurements are taken from a photo · methodology · all insights