1. The landmark model
Every tool starts with Google's MediaPipe Face Landmarker, a neural network that predicts 478 three-dimensional points on a face from a single image: 468 for the face surface (Kartynnik et al., 2019) plus 10 for the irises (the attention-mesh refinement, Grishchenko et al., 2020). It runs inside your browser through WebAssembly, on the GPU where available and on the CPU otherwise. The model file is downloaded from Google's servers; your photo is not sent anywhere.
MediaPipe returns coordinates normalized to the image's width and height. We first convert them to true pixel space so that a portrait or landscape photo can't stretch any ratio.
2. Pose checks and head-roll normalization
Before measuring, the scanner rejects photos that would give misleading numbers. A head turned to one side is detected from the nose-tip distance to each cheekbone: if |left − right| ÷ (left + right) exceeds 0.14, you're asked to face the camera. Very dark or bright photos, a face that fills too little of the frame, an open mouth or a smile are flagged too, because each one moves specific landmarks.
Head tilt (roll) is corrected rather than rejected. We measure the angle of the line through the two iris centers and rotate every point around the brow center until that line is horizontal:
θ = atan2(y473 − y468, x473 − x468)
p′ = rotate(p, around L168, by −θ)All ratios, angles and the symmetry midline are measured on these levelled points.
3. Calibration to the reference scale
Classical norms (Farkas, 1994) measure from true anatomical points: the hairline, the brow line, the jaw corner. MediaPipe's nearest landmarks sit slightly inside those points, so raw mesh ratios read every face as shorter, broader and squarer than it is. Five ratios are therefore mapped linearly onto the reference scale, reference = refMean + (raw − meshMean) × spread, using these constants:
| Ratio | Mesh mean | Reference mean | Spread |
|---|---|---|---|
| Length ÷ width | 1.2 | 1.426 | 1 |
| Forehead ÷ cheekbones | 0.73 | 0.83 | 1 |
| Jaw ÷ cheekbones | 0.885 | 0.8 | 2 |
| fWHR | 2.15 | 1.88 | 1 |
| Jaw angle (°) | 137 | 125 | 1 |
The mesh means come from MediaPipe's canonical face model and a small set of early scans; the reference means from published norms and our celebrity reference set. Both will be re-fitted as more data becomes available. Raw values are stored with every scan so results can be recomputed.
4. The 11 proportions and the harmony score
Each proportion is scored 0–100 by how close it is to its reference value, using a Gaussian curve: score = 100 · e^(−½ · ((value − target) ÷ tolerance)²). A measurement exactly on target scores 100; one tolerance away scores about 61; two tolerances away about 14. Symmetry and thirds use their own exponential curves, shown below.
| Proportion | Formula (MediaPipe indices) | Target ± tolerance | Weight |
|---|---|---|---|
| Bilateral symmetry | 100 · e^(−3.2·D), D = mean mirrored discrepancy of 12 landmark pairs ÷ ½ cheekbone width | 88–100 band | 20% |
| Facial thirds balance | Σ |third − ⅓| over 10→168, 168→2, 2→152 (each ÷ 10→152) | 100 · e^(−dev ÷ 0.09) | 14% |
| Canthal tilt | atan2(y_inner − y_outer, |x_outer − x_inner|), mean of both eyes | +5.5° ± 4° | 10% |
| fWHR | |234 − 454| ÷ |168 − 0| (calibrated) | 1.90 ± 0.18 | 8% |
| Length-to-width | |10 − 152| ÷ |234 − 454| (calibrated) | 1.45 ± 0.14 | 10% |
| Midface ratio | |468 − 473| ÷ vertical pupil-line → 0 | 1.00 ± 0.08 | 10% |
| Eye spacing | |468 − 473| ÷ |234 − 454| | 0.46 ± 0.03 | 8% |
| Jaw-to-cheek | |58 − 288| ÷ |234 − 454| (calibrated) | 0.80 ± 0.09 | 7% |
| Nose width | |102 − 331| ÷ |133 − 362| | 1.00 ± 0.16 | 5% |
| Mouth-to-nose | |61 − 291| ÷ |102 − 331| | 1.55 ± 0.22 | 4% |
| Jaw angle | angle 234–58–152, mean of both sides (calibrated) | 125° ± 14° | 4% |
The weighted average W of the 11 scores becomes the harmony score, clamped to 35–98 so a single photo can never claim a perfect or a minimum result:
harmony = clamp(21 + 0.68 · W, 35, 98)Benchmark percentiles on tool pages are modelled, not observed: a score is mapped through a normal distribution with mean 60 and standard deviation 18. We don't build a database of user faces, because selfies are deleted within hours and free results after 48 hours.
5. Face shape
Face shape uses three calibrated ratios: length ÷ cheekbone width, forehead ÷ cheekbone width and jaw ÷ cheekbone width. We compute a weighted distance to six prototypes (oval, round, square, heart, diamond, oblong) taken from the average ratios of our celebrity reference set, add small priors for unambiguous cases (for example, length ÷ width of 1.55 or more favors oblong), and turn the distances into a probability for each shape. That's why results show a main shape and how close you are to the others.
6. What runs where
- On your device: the landmark model, every formula on this page, face shape, celebrity bone-structure matching and every free tool.
- On our servers, only with your consent: the 12-season color analysis and the try-on images, which need the photo itself. That path, and how the photo is deleted, is explained on privacy & security.
7. Limitations
- 2D projection of a 3D face. Depth is estimated, not measured, so ratios that depend on depth (side profile, jaw angle) are approximations.
- Lens and distance. A phone held closer than about a metre enlarges the nose and center of the face and narrows the sides. Wide-angle front cameras exaggerate this.
- Pose and expression. Small head pitch changes the thirds and canthal tilt; a smile lifts the outer eye corners and widens the mouth; a turned head breaks symmetry.
- Hair and occlusion. A fringe, glasses or a beard hide or shift landmarks such as the upper forehead and jaw corners.
- Reference norms. Classical norms were collected from specific populations; proportions vary naturally between people of different ancestry, ages and sexes, and none of that variation is a flaw.
- Not medical. The tools describe geometry for styling purposes. They are not a medical, psychological or orthodontic assessment, and we never recommend procedures.
Every tool page shows the specific formula, landmarks and reference bands it uses, plus how to take the same measurement by hand. Start with the free tools or read our editorial policy.