Dark circles under the eyes
Under-eye darkness (ΔL*)

How much darker the skin under the eye is than the skin in the middle of the cheek, as a difference in mean lightness.

Also searched as under-eye darkness, dark under eyes and periorbital hyperpigmentation.

Confidence
Skin · lighting-dependent
Unit
ΔL*
Region
infraorbital vs mid-cheek
CI floor
—
canvas pixel analysis in CIE L*a*b* — see methodology
Measure yours →
Illustration · on your scan the same lines are drawn on your own photo

How to read it

Below the mean

the skin under the eye reads distinctly darker than the mid-cheek.

Near the mean

the skin under the eye reads a little darker than the mid-cheek.

Above the mean

the skin under the eye reads close to the mid-cheek in lightness, or lighter than it.

Caveat

Strongly lighting-dependent (overhead light deepens it). Compare only across photos taken under the same light.

Why every value has an error bar

Every value Canthion reports carries a 1σ uncertainty propagated from MediaPipe Face Mesh's published accuracy (3.96% of inter-ocular distance mean absolute error per landmark, Kartynnik 2019). On a typical photo with 300 px between the pupils, that is about 12 px of wander on every point. Small ratios and angles inherit it, so their intervals are wide. A number without an interval is a number pretending to be more precise than it is.

References
  • Sano & Kawabata (2023). A computational approach to investigating facial attractiveness factors using geometric morphometric analysis and deep learning. Sci Rep 13:19797. doi.org/10.1038/s41598-023-47084-x

Common questions

What are dark circles under the eyes?

How much darker the skin under the eye is than the skin in the middle of the cheek, as a difference in mean lightness. More negative = darker under-eye. Under-eye appearance is one of the regions CNN saliency studies find raters attend to most.

How are dark circles under the eyes measured from a photo?

From the pixels of the photograph, not from landmarks: the region (infraorbital vs mid-cheek) is converted to CIE L*a*b* and the value is read as a statistic of those pixels. Because it depends on lighting, it is reported relative to the rest of the same photograph and marked lighting-dependent.

How reliable are dark circles under the eyes from a photograph?

Strongly lighting-dependent (overhead light deepens it). Compare only across photos taken under the same light.

The rest of the skin set, then the nearest measurements elsewhere on the face. Every one is computed on the same photograph, in the same run, with its own error bar.

Also: how bone-level measurements are taken from a photo · methodology · glossary · all 35 insight pages