What this experiment shows

Increasing mouth width increases mouth/nose and decreases cheek/mouth. Their proximity scores need not improve together. The summary also includes face length/cheek width and eye gap/eye width; the latter uses 1.00, not 1.618, as its reference.

Inputs and method

Starting from the synthetic coordinate fixture, we scale the distance between the two mouth-corner landmarks by 0.70, 0.85, 1.00, 1.15 and 1.30 around the image centre. All other coordinates and photo signals stay fixed. We report the actual calculator's mouth/nose and cheek/mouth ratios, their reference-proximity scores and the four-ratio average.

Calculation version: ARF calculation experiments 1.0. Engine: ARF Local Geometry v3.0.

Calculated results

Four-ratio average / 100050100Mouth width factor: 0.7; Four-ratio average / 100: 620.7Mouth width factor: 0.85; Four-ratio average / 100: 710.85Mouth width factor: 1; Four-ratio average / 100: 741Mouth width factor: 1.15; Four-ratio average / 100: 741.15Mouth width factor: 1.3; Four-ratio average / 100: 741.3Mouth width factor
Calculated from the published inputs. The full values and configuration details are in the table below.
5 calculated configurations. Scores use the site's 0–100 scale; match shares and enlargement are percentages.
Mouth width factorMouth / noseProximity / 100Cheek / mouthProximity / 1004-ratio average
0.71.26764.444462
0.851.53953.662271
11.8903.1113874
1.152.07772.7055174
1.32.34652.3936374

Download this table (CSV) · Reproduce the calculation

How to use this when reading your result

Read each ratio before reading the average. The calculator reports proximity to selected targets and chosen tolerances. It does not measure how attractive you are, and a different choice of targets or weights would produce a different summary from the same face.

Inspect your facial ratios →

What this experiment cannot tell you

Moving two synthetic coordinates is not a simulation of anatomy, a cosmetic intervention or a real expression. These results test the calculator's arithmetic only. The cited research provides context for measurement limits; it does not validate this site's targets or formula.

Sources and calculation choices

  • New “golden” ratios for facial beauty — Pallett, Link & Lee, Vision Research (2010). An example of a study of particular feature arrangements and preference judgments. Its measured arrangements are not a general endorsement of 1.618, our four selected ratios, or a universal beauty score.
  • The role of the golden proportion in the evaluation of facial esthetics — Rossetti et al., The Angle Orthodontist (2013). Context for the limits of treating selected facial ratios as an attractiveness standard. Results from one study and one measurement protocol should not be generalized to every face, culture or photo.

See the full source notes and methodology. To report an error, contact us with the page URL and the input or calculation that appears wrong.