Anthropometry · Multi-Ethnic Framing

Caucasian facial features

RealSmile Research Team · Facial Analysis Specialists
Updated May 16, 2026
Based on 5 peer-reviewed sources
→ See our methodology

How a face with European ancestry scores across 17 structural metrics. Descriptive anthropometry, not a hierarchy.

Beauty is multi-ethnic. Published cross-cultural research finds no population scores higher than another in aggregate. This page describes the distribution within European ancestry, not a ranking against other ethnicities.

17 metrics · Farkas European norms · Free · No signup

Free score · $14.99 unlocks European sub-population context

Why a single European norm is not the right reference

The phrase Caucasian facial features sounds like it points to a single distribution. The published European craniofacial work shows otherwise. The Farkas international comparison (Farkas et al. 2005) documents measurable variance between Northern European, Mediterranean, Eastern European, and other regional sub-populations on nasal index, palpebral fissure width, midface projection, and lower-face proportion. Treating all European ancestry as one mean would lose this variance the same way treating all populations as one mean would lose cross-population variance.

The 17-metric report carries both the universal percentile (cross-population) and the European-distribution percentile (within-Caucasian, drawing on sub-population norms where validated datasets exist). The gap between them tells you whether the metric you are looking at is doing the heavy lifting against the general distribution or just against your sub-population.

The 17 metrics themselves are universal geometry. Facial thirds, fifths, FWHR, canthal tilt, jawline ratio, lip ratios, philtrum length, eye aspect ratio, brow-to-eye distance, nasal index, midface ratio, and the rest are defined the same way regardless of population. The reference distribution changes; the measurement does not.

5 structural patterns documented in European craniofacial research

Nasal index variance

Northern European and Mediterranean nasal-width-to-height norms sit in distinct sub-ranges (Farkas et al. 2005). The population-appropriate percentile carries this variance rather than collapsing to a single European mean.

Palpebral fissure width

Average eye aperture width sits in a documented Caucasian sub-range, with measurable variance between Northern, Eastern, and Mediterranean European populations. The score reads this against the closest sub-population norm where available.

Midface projection

Average midface projection sits higher than several non-European reference samples but with internal variance across European sub-populations. Carried as descriptive percentile rather than as a universal target.

Lower-face proportion

Lower-face height relative to total facial height clusters in a documented sub-range with regional variance. Reads against the European-distribution norm in the paid report.

Skin tone and freckling

Skin tone is not a structural metric in the composite. The score does not reward or penalize lighter skin; it measures geometry. The texture-and-tone layer in the paid report describes what the camera is seeing without ranking against population norms.

Hair color and density

Hair color and density shift how the brow-to-eye distance metric reads (lighter brow hair often under-represents brow density to the detector). The score treats this as a measurement artifact and carries a confidence range rather than a single percentile when brow hair is very light.

📊

Recommended next step

Get the Breakdown Behind Your Score

Instead of a single number, see 17 individual metrics — jawline, canthal tilt, symmetry, and more.

Why we publish the European-distribution norms openly

Most face tools that score against European norms do so implicitly. The reference distribution is buried in the model and the user has no way to know what they are being scored against. We publish the norms openly. The Farkas atlas is the underlying source; the sub-population datasets are cited where they are used.

Open norms make the score auditable. If your population-appropriate percentile and universal percentile diverge sharply, you can check the underlying norms and see whether your specific sub-population is well-represented in the European-distribution dataset. If it is not, the universal percentile is the more honest read.

Honest limits of any ethnicity-aware face score

Caucasian facial features FAQ

Does this page rank Caucasian faces against other ethnicities?+
No. Beauty is multi-ethnic, and the published cross-cultural preference research (Cunningham et al. 1995; Rhodes 2006; Coetzee et al. 2014) finds no single ethnicity scores higher than another in aggregate. This page describes how the 17 structural metrics tend to distribute across faces of European ancestry. The composite uses population-appropriate reference distributions in the paid report rather than treating one population as a universal target.
Why bother with a Caucasian-specific page if most face tools default to Caucasian norms?+
Two reasons. One: many tools default to those norms implicitly, but few state it openly, which makes it hard for a user to know what reference distribution they are being scored against. Two: European ancestry itself spans Northern, Southern, Eastern, Western, and Mediterranean populations with distinct craniofacial sub-distributions. The published European norms (Farkas 1994 atlas; Farkas et al. 2005 international comparison) document this variance even within the Caucasian category.
Which structural metrics tend to vary within European populations?+
Nasal index, palpebral fissure width, midface projection, and lower-face proportion all show measurable variance across Northern European, Mediterranean, Eastern European, and other regional sub-populations (Farkas et al. 2005). The variance within Caucasian is large enough that population-appropriate percentiles still matter even for users whose ancestry sits squarely in the European category.
Are the percentiles compared to European norms or universal norms?+
Both, in the paid report. The free composite shows your score against the universal cross-population distribution. The $14.99 Looksmax Report adds a per-metric percentile against published European-distribution norms (Farkas atlas, Czech, German, Italian, and other regional datasets where available). The dual percentile is the useful read.
Is my photo uploaded?+
No. The 68-landmark detector runs entirely in your browser. The 17-metric vector is computed on your device and never leaves it. Open the network tab during a scan to verify zero image bytes leave the browser.
Does the test work on Mediterranean, Middle Eastern, or Slavic faces?+
Yes. The 17-metric geometry is universal. The interpretation layer uses the published European norms where the underlying anthropometric work specifically sampled those populations. Mediterranean and Middle Eastern norms (Ferrario et al. on Italian samples; multiethnic atlases on Levantine samples) sit in the broader Caucasian category but with sub-population variance. The composite carries this rather than collapsing all European-ancestry faces to a single mean.
What does the free score include and what does the $14.99 report add?+
Free: composite 0 to 100, universal percentile, and your two strongest plus two weakest metrics. Paid ($14.99 Looksmax Report): every metric percentile against both universal and European-distribution norms, a 5-page written breakdown of which metrics are doing structural heavy lifting in your specific face, and a soft-tissue-first improvement plan.

Free score is the headline. Sub-population context is the plan.

Get all 17 metrics with European sub-population context.

The $14.99 Looksmax Report scores all 17 metrics with both universal and European-distribution percentiles, identifies your two weakest metrics, and writes a soft-tissue-first plan.

Score your face now

Free, instant, private. 17 metrics with sub-population percentile context in the paid report.

17 metrics · Farkas European norms · Photos auto-deleted

Related Tools

Improve your results

Try our other tools

All free. All private. All instant.