Face Report: Free 17-Metric Instant Face Report

Axis 1: Symmetry

Symmetry is measured by mirroring 34 paired landmark points (left vs right eye corners, brow points, alar bases, oral commissures, jaw points) across the vertical facial midline and computing the Euclidean displacement at each pair, normalized by interpupillary distance so the score is independent of camera distance. The face report then averages those 34 displacements into a single symmetry sub-score on the 0–100 scale.

This matters because symmetry is one of the few cross-cultural, cross-method-validated correlates of rated attractiveness in the academic literature; Rhodes (2006) (NIH PMC2781897) is the canonical review. But the same review documents a plateau effect: beyond moderate symmetry, additional symmetry buys very little additional attractiveness rating. So the face report flags significant asymmetry as actionable (often photo-controllable: head-tilt, off-center camera, resting expression) but does not weight perfect symmetry heavily once you cross the moderate-symmetry threshold.

In the face report you see the symmetry sub-score, which paired landmarks contributed most displacement, and a flag if the asymmetry signature looks photo-induced vs structural. Re-shooting with a level camera and a relaxed expression typically moves the symmetry sub-score 10–20 points without anything changing about your face.

Axis 2: Harmony (composite proportion read)

Harmony is the composite axis. It does not measure a single distance; it measures how the other 16 sub-metrics integrate. Specifically the face report checks for variance: a face that scores 90 on jawline, 90 on cheekbones, and 50 on midface ratio reads less harmonious than a face scoring 75 on all three, because the eye notices the outlier. Harmony is the variance-penalized average of the other 16 axes, so it rewards balanced features over single-metric extremes.

In the face report harmony shows up as the second-most-weighted axis after smile authenticity, and the report calls out which one or two outlier sub-metrics are dragging your harmony number down. This is usually the most actionable finding in the whole face report. The highest- leverage fix is rarely the lowest sub-score, it is the sub-score that is out of step with the rest of your face.

Axis 3: Proportion (facial thirds, midface ratio, golden-ratio compliance)

Proportion is three sub-metrics rolled together in the face report: facial thirds (Jefferson 2004; forehead, midface, lower-face vertical spans), midface ratio (Marquardt 2002; glabella to subnasale normalized by total face height), and golden-ratio compliance (Marquardt-mask alignment across 12 landmarks). All three are computed from the same 68 landmark points, normalized by interpupillary distance, and reported as separate sub-scores plus a combined proportion read.

Proportion matters because it explains a substantial chunk of the harmony score. The face report is explicit that golden-ratio compliance is a reference, not a verdict. Academic support for the golden ratio as predictive of rated attractiveness is contested. We include it because users ask for it and because it is useful as a comparative read across photos of the same person, not as an absolute statement that any specific proportion is required. For the deeper companion piece, see our golden-ratio facial proportion deep-dive for the literature review, and our evidence-based facial proportion breakdown for the cross-metric proportion picture.

Axis 4: Skin / surface read

The face report does not run a clinical skin-condition diagnosis (that requires dermoscopy, controlled lighting, and a trained clinician). Instead the face report reads three surface signals from the photo itself: luminance variance across forehead and cheek regions (a proxy for even skin tone in the photo), specular highlight distribution (a proxy for whether the lighting is flattering), and contrast variance at the brow and lip border (a proxy for whether the photo is rendering features with definition or washing them out).

In the face report this axis is intentionally framed as a photo read, not a skin verdict. If your skin axis comes back low, the report tells you the lighting is doing the damage and recommends a re-shoot in north-facing window light or with diffused front lighting, not a skincare regimen. This is a deliberate boundary: a single photo is not enough information to judge skin condition, and we will not pretend otherwise.

Axis 5: Smile authenticity (Duchenne markers)

Smile authenticity is the heaviest-weighted axis in the face report, because the first-impression literature consistently finds that expression dominates the read at the first-second look. The face report scores Duchenne markers: AU6 (cheek raise, orbicularis oculi engagement) and AU12 (lip-corner pull, zygomaticus major engagement) per the Ekman & Friesen FACS framework. A genuine smile fires both AU6 and AU12; a polite or held smile fires AU12 alone.

In the face report you see the AU6 and AU12 sub-scores separately, plus a smile authenticity composite. If AU12 is high but AU6 is low (the classic forced-smile signature), the report flags it and recommends the re-shoot prompts that reliably trigger a Duchenne smile: recall a specific funny memory, count down from three with eyes closed and open on zero, or take the photo mid-laugh rather than mid-pose. Most users move the smile authenticity score 20+ points across two photos shot minutes apart with these prompts.

Symmetry research and the plateau effect

Facial symmetry is one of the more replicated correlates of rated attractiveness in the academic literature. Rhodes (2006) (NIH PMC2781897) is the canonical review and reports a small-to-moderate positive correlation across multiple methods (rated symmetry, manipulated symmetry, fluctuating-asymmetry composites). Research suggests symmetry matters most when it is broken, not when it is perfect: above moderate symmetry the rating gain plateaus, which is why the face report flags significant asymmetry as actionable but does not reward perfect symmetry with extra weight.

Followup work on perceived symmetry and judgments of facial attractiveness (NIH PMC2826778) also documents that perceived symmetry, the symmetry a viewer reads off a photo, is partly photo-induced (head tilt, lighting, off-center framing) rather than purely structural. That is why the face report separates a photo-induced asymmetry flag from a structural asymmetry flag and recommends a re-shoot before any structural interpretation.

Averageness, FWHR, and dominance signaling

Averageness (a face whose proportions cluster near the population mean) is associated with higher rated attractiveness in multiple cross-cultural samples (Langlois & Roggman 1990; Rhodes 2006). FWHR (facial width-to-height ratio) is a separate marker tied more closely to dominance perception than to attractiveness directly (Carre & McCormick 2008, PMID 18596419). The face report measures both, but weights averageness inputs (facial thirds, midface ratio) into the proportion axis and FWHR into a dominance-signal axis rather than collapsing them into one number.

This separation matters because averageness and dominance are different reads. A face can be high-FWHR and average-proportion at once, or high-averageness with low-FWHR. The face report surfaces both reads separately so the user can decide which one is relevant to the photo context (a LinkedIn headshot, a dating-app lead photo, a casting profile picture each weight these reads differently).

Marquardt mask and the golden ratio (a hedged inclusion)

Marquardt (2002) proposed a phi-based facial mask aligning twelve landmark points to ratios derived from 1.618. Marquardt-mask alignment is widely cited in cosmetic and craniofacial reference work, but empirical support for the golden ratio as a strong predictor of rated attractiveness is contested. Several replication attempts find weak or null effects once symmetry and averageness are controlled for (Holland 2008, PMID 16313657 and follow-ups). The face report includes golden-ratio compliance as a sub-score because users routinely ask for it and because it is informative as a comparative read across photos of the same person, not because it is a settled predictor.

The face report labels this axis as reference rather than verdict. If the methodology section flags golden-ratio compliance as the lowest sub-score, the report explicitly recommends ignoring that axis as a standalone signal and reading the harmony composite instead. We document this so the user knows where the evidence is strong and where it is partial.

Smile authenticity and Duchenne markers

Smile authenticity is the heaviest-weighted axis in the face report because the first-impression literature (Willis & Todorov 2006, PMID 16866745) consistently finds that expression dominates the read at the first-second look, often over structural geometry. The face report scores Duchenne markers per the Ekman & Friesen FACS framework: AU6 (cheek raise, orbicularis oculi engagement) and AU12 (lip-corner pull, zygomaticus major engagement). A genuine smile fires both AU6 and AU12; a polite or held smile fires AU12 alone, and viewers reliably read the difference even when they cannot verbalize it.

Because the literature on Duchenne markers is well replicated and the axis is highly photo-controllable, the face report weights smile authenticity as the largest single contributor to the composite. Users who re-shoot with a Duchenne-trigger prompt (recall a specific funny memory, take the photo mid-laugh rather than mid-pose) routinely move the smile axis 20+ points across photos taken minutes apart. This is the most actionable axis in the whole face report.

A score above 80 is associated with strong photo signals, not a guarantee

Research suggests faces in the 80 to 100 band typically score high on symmetry, harmonious thirds, and a Duchenne-validated smile. That cluster may correlate with stronger first-impression ratings on dating-app and LinkedIn-style read tasks (Willis & Todorov 2006). It does not guarantee any specific outcome: match rate, callback rate, or partner-selection results depend on context (the platform, the audience, the bio, the other photos in the set) that the face report cannot see from a single image. Treat a score above 80 as a green light to use the photo, not a promise of any particular result.

A score in the 60 to 80 band usually flags two or three fixable axes

Faces in the above-average band almost always have two or three specific sub-metrics that are dragging the composite. Research suggests the fastest gains live in photo-controllable axes (smile authenticity, symmetry, lighting) rather than structural ones, because expression and framing dominate the first-impression read. The face report names the one or two highest-leverage fixes rather than telling you to fix every weak metric. A user who reshoots with a Duchenne prompt and a level camera angle frequently moves into the 80-plus band on the next photo.

A score in the 40 to 60 band is most often a photo problem, not a face problem

Research suggests that scores in the average band are most commonly driven by harsh lighting, off-center framing, a held or polite smile, or a tilted camera angle, all of which the face report flags as photo-induced rather than structural. The hedged read is that the face report cannot tell you a 40 to 60 score reflects your face, only that it reflects this specific photo of your face. Re-shooting in north-facing window light with a relaxed expression and the camera at eye level routinely lifts the same person 20 to 30 points across two photos.

A score below 40 almost always means re-shoot before drawing any conclusion

Scores in the photo-issue band are typically associated with a forced expression, severe specular highlight (washed-out lighting), or an unflattering camera angle. The face report explicitly does not interpret a sub-40 score as a structural read. Research suggests that two photos of the same person taken minutes apart can swing 30 plus points purely on lighting and expression. The face report recommendation is to re-shoot first and only then interpret the score.

What the score is not predictive of

The face report is a single-photo, 17-metric photo read. It is not predictive of long-term partner selection, relationship satisfaction, professional outcomes, or anything that depends on context the face report cannot see. Research on the first-impression literature is clear that initial reads explain a portion of variance in rapid-judgment tasks, but a much smaller portion of variance in actual relational or professional outcomes (which are dominated by behavior, not appearance). The face report is a useful comparative tool for picking a photo. It is not a useful tool for predicting your life.