Face Shape Detector
Find your face shape from four measurements rather than a chart you hold up to the mirror. The detector compares your forehead, cheekbone and jaw widths against your face length — in your browser, without uploading the photo.
- No signup
- No upload
- Free
- ~10 seconds
Click to choose a photo, or drop one here
Straight-on, even lighting, at arm's length gives the most comparable reading.
No photo to hand? Try one of these and see what the tool returns.
Runs in your browser. Your photo is never uploaded.
What decides your face shape?
Four measurements: forehead width, cheekbone width, jaw width, and face length from hairline to chin. Each of the seven shapes is a specific relationship between those numbers — an oval is long with a narrow jaw, a round is nearly as wide as it is long, a diamond has cheekbones wider than both other widths.
- There are seven standard shapes: oval, round, square, heart, oblong, diamond and triangle.
- A round face has a length-to-width ratio under 1.2; an oblong is above 1.6.
- Many detectors check the round condition before the square one, which makes square unreachable — this one checks the narrower condition first.
- Camera angle changes the result: a low angle widens the apparent jaw and can turn an oval into a reported round.
What is my face shape? The four measurements that decide it
Face shape is not a vibe, it is a ratio problem. Four numbers settle it: forehead width, cheekbone width, jaw width, and face length from hairline point to chin. Every one of the seven shapes is a specific relationship between those four.
An oval face is long relative to its width with a jaw narrower than the cheekbones. A round face is close to square in proportion with a soft jaw. A diamond has cheekbones wider than both ends. Once you have the measurements, the label follows automatically — which is why a detector beats holding a printed chart against a mirror.
How to determine face shape without measuring by hand
The manual method is a tape measure, a mirror and four written-down numbers. It works, and it is tedious enough that almost nobody finishes it.
This detector places 478 landmark points on your photo and takes the same four measurements from them, in about a second. The landmarks are the same ones the manual method aims at — the outer brow points, the widest point of the cheekbone, the jaw angle, and the chin.
Face shape analyzer results: why square is so rarely reported
Most implementations check the round condition before the square one. Because the round threshold is looser, every square face satisfies it first and the square branch never executes. A great many people have been told they have a round face by tools that were structurally incapable of saying anything else.
Ours checks the narrower condition first, so square is reachable. If you have been repeatedly told round and never believed it, this is worth a re-run.
Face shape detector online, with nothing uploaded
The face mesh model downloads to your browser and the measurements are computed on your device. Your photo is never transmitted and never stored.
For a face shape reading, angle matters more than most people expect. A phone held low widens the apparent jaw and can flip a genuine oval into a reported round. Straight on, at arm's length, in even light.
Face shape detector vs measuring with a tape
A tape held against your own face is accurate to perhaps half a centimetre, which is plenty for a clear case and useless for a borderline one. It is also very hard to keep your head straight while measuring, so the horizontal widths drift in one direction while the vertical stays put — which pushes results toward oval and oblong.
The detector takes the same four measurements from 478 landmarks in one pass, so the three widths are read at the same instant from the same head position. It inherits a different weakness instead: it is only as good as the photo, and a turned head fools it in exactly the way a turned head fools a tape. Neither method escapes the angle problem, which is why the advice on both is the same — straight on, eye level, hair back.
What the detector reports when your face sits between two shapes
Roughly a fifth to a third of faces fall near a boundary, and the categories genuinely overlap there. Round and square share the same proportions and differ only in whether the jaw turns a corner; oval and oblong are both long and differ only in whether the jaw tapers. A face in one of those bands can be labelled either way without either label being wrong.
The tool reports the shape whose condition is met most clearly and shows you the underlying widths, so you can see how close the call was. If your two most likely shapes are the pair above, reading both type pages is more useful than trusting the label — the styling advice for round and square diverges, and knowing which side of the line you are on matters more than the name.
Tips for an accurate face shape reading
- Pull all hair back, including a fringe. The measurement uses your brow and jaw landmarks, but hair over them makes the detection less stable.
- Straight on and at eye level. A low camera angle widens the apparent jaw enough to turn an oval into a reported round.
- Neutral expression — a smile moves the cheekbone landmarks outward.
- Even lighting so the jaw edge is visible on both sides.
Face Shape Detector — frequently asked questions
Can I use a photo with glasses on?
Better not to. Frames sit across the widest part of the face and can obscure the cheekbone landmark, which is the reference measurement the other two are compared against.
Does the detector work on a side profile?
No. Every measurement it takes is a horizontal width read against face length, and a turned head compresses those widths on one side. It needs a straight-on photo.
Is this face shape detector free?
Yes, and no account is needed. The detection and the full measurement breakdown are free.
How accurate is an AI face shape detector?
The measurements are exact. The labels are a convention laid over a continuous distribution — plenty of faces sit near a boundary, and those can legitimately be described two ways.
Why did I get a different face shape on another site?
Different tools use different thresholds and different landmark points for the same named measurement. Borderline faces flip between labels as a result.
What are the seven face shapes?
Oval, round, square, heart, oblong, diamond and triangle. Some charts merge triangle into pear or add rectangle as a separate entry from oblong.
Does hair or a beard change the result?
It should not — the landmarks sit on facial features, not the hairline or beard outline. A very heavy beard can obscure the jaw angle enough to shift the measurement, so pull hair back if you can.
References
- 1.Rhodes, G. (2006). The evolutionary psychology of facial beauty. Annual Review of Psychology, 57, 199–226.