Insights · Whole face · Measurement

Facial fifths

Face width divided into five segments: outer face → outer canthus, eye length, intercanthal, eye length, outer canthus → outer face.

Confidence
Tier A · tight interval
Unit
segments
Landmarks
zy_R, ex_R, en_R, en_L, ex_L, zy_L
CI floor
± 1
[dist(zy_R,ex_R), dist(ex_R,en_R), dist(en_R,en_L), dist(en_L,ex_L), dist(ex_L,zy_L)] / dist(zy_R,zy_L)
Measure yours
Illustration · on your scan the same lines are drawn on your own photo

How to read it

Fifths are reported as a description of horizontal layout, not as a target. The outer fifths depend on where the face edge is located, which in a 2D photo is the silhouette rather than the zygion.

The neoclassical claim: Five equal fifths (20% each)

The middle fifth (intercanthal) exceeds the eye-length fifths in most East Asian and many other adults. Descriptive only.

Conformity in published samples: na white 41% · east asian 0%

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, Hreczko, Kolar & Munro (1985). Vertical and horizontal proportions of the face in young adult North American Caucasians: revision of neoclassical canons. Plast Reconstr Surg 75(3):328–338. pubmed.ncbi.nlm.nih.gov/3883374/
  • Jayaratne, Deutsch, McGrath & Zwahlen (2012). Are Neoclassical Canons Valid for Southern Chinese Faces? PLoS ONE 7(12):e52593. doi.org/10.1371/journal.pone.0052593

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