Free tool · runs in your browser
Measure the gap between your inner eye corners and compare it with the average width of your two eyes. See the distances drawn on your photo and understand the one-eye-width comparison.
Drop a photo, paste one, or choose a file
Straight-on, whole face visible, even light. JPG, PNG or WebP.
Runs in your browser. Your photo never leaves your device.
NewSymmi Lab · full face analysis
Your eyes, brows and lashes read in full, the haircut and brow shape that make them stand out, plus your score, your colours and your plan.
$14.99 once · no subscription · ready in minutes

Sample result
Understand the comparison
These schematic examples hold both eye widths constant and change only the gap. Real faces can differ in all three distances. The examples are not category boundaries.
The historical orbital canon compares inner-corner distance with eye width. Research documents substantial variation, so equality should not be treated as a universal target. Our ratio describes this photo; it does not diagnose eye spacing or infer anatomy from a population average.
Sources: study of facial canons and systematic review of intercanthal distance.
How it is measured
The gold line joins the inner eye corners. Each blue line joins the inner and outer corners of one eye. All three are straight-line distances in the image; the average of the two blue lengths is the denominator. This ratio is unchanged by geometrically rotating or uniformly resizing the same points, although a new model detection may place those points slightly differently.
Sources
The measurement and its reference ranges come from published research. Studies use different methods and populations, so compare your number with the range shown on this page rather than with other tools.
Bouhadana G, Gornitsky J, Saleh E, et al. (2022). Expanding the classic facial canons: quantifying intercanthal distance in a diverse patient population. Plastic and Reconstructive Surgery Global Open. PubMed 35475286
Inner-eye-corner distance measured in a diverse population.
Al-Sebaei MO (2015). The validity of three neo-classical facial canons in young adults originating from the Arabian Peninsula. Head & Face Medicine. PubMed 25889948
Tested the 'one eye width apart' canon on real faces.
Farkas LG, Katic MJ, Forrest CR, et al. (2005). International anthropometric study of facial morphology in various ethnic groups/races. Journal of Craniofacial Surgery. PubMed 16077306
Eye-region measurements across ethnic groups.
Kartynnik Y, Ablavatski A, Grishchenko I, Grundmann M (2019). Real-time facial surface geometry from monocular video on mobile GPUs. arXiv. arXiv:1907.06724
The face-mesh model that places the 468 surface landmarks this tool measures from.
Ablavatski A, Vakunov A, Grishchenko I, et al. (2020). Real-time pupil tracking from monocular video for digital puppetry. arXiv. arXiv:2006.11341
The iris model that adds 10 eye landmarks (478 in total), used for pupil-based reference lines.
Our own data: how much each reading moves when the same face is photographed again is published on the methodology page. How we choose sources.
Related tools
Pupillary Distance Tool
Your PD in millimetres, no card needed.
Lash Map Tool
The lash map that suits your eye shape.
Eye Shape Guide & Self-check
Compare eyelid crease, outline and corner direction separately.
Canthal Tilt Calculator
Measure eye-corner direction, one eye at a time.
Facial Ratios Calculator
Find the separate pupil-span-to-face-width reading.
FAQ
A common visual comparison looks at the inner-corner gap relative to one eye width. A larger gap is often described as wider-set and a smaller gap as closer-set. This tool reports the ratio using the average width of both eyes, without applying a clinical or beauty cutoff.
No. The one-eye-width rule is a historical facial proportion convention, not a universal normal range or an attractiveness target. Published measurements show variation across individuals and populations. A ratio above or below 1.00 is not by itself a problem.
No. Interpupillary distance runs from pupil centre to pupil centre. ESR in Symmi's facial-ratios tool divides that distance by cheekbone width. This page divides the inner-corner gap by average eye width; these numbers should not be compared as if they used the same formula.
The two eye widths can differ in a photo. Averaging makes the reference explicit rather than choosing one side, and the individual widths remain visible so you can check them.
Yes. Turning your face, perspective, squinting, obscured corners and landmark placement can change the estimate. Use a front-facing photo with an eye-level camera and even light. Roll alone does not change the straight-line geometry, but a different image can change detection.
No. This is a unitless photo proportion and does not provide calibrated pupil distance in millimetres for fitting lenses.
No. Landmark detection, measurement and annotation run in your browser.
A controlled scan, every reading against its ideal band, bone vs trainable, a plan, and a 3D model on Face ID iPhones.

Symmi Lab · new
Your full face analysis, with 4 haircuts on your own face.