Welsh skin tone: Fitzpatrick type and undertone in 66 observed portraits

Welsh: fitzpatrick skin type II in 94% of 66; undertone warm in 70% of 64.

  • Welsh catalog portrait, AI-generated, skin tone in view

Catalog portraits for Welsh are AI-generated adult subjects; the measurements on this page come from documented photographs of real people, not from these images.

Fitzpatrick skin type

n = 66 assessable

Six-class ordinal classification of constitutive skin pigmentation, originally developed for sun-reactivity assessment but now the de-facto skin-tone vocabulary in dermatology and computer-vision fairness research.

ValueSharen
IAlways burns, never tans. Pale white skin, often with red or blonde hair, blue/green eyes, freckles. Common in Northern European populations of Celtic / Scandinavian descent.2%1
IIBurns easily, tans minimally. Fair skin, light hair, light eyes. Common in Northern European populations.94%62
IIISometimes burns, gradually tans. Light olive to medium skin tone. Common in Mediterranean European, Middle Eastern, and East Asian populations.3%2
VRarely burns, tans deeply. Brown skin tone. Common in South Asian, North African, Middle Eastern, some Latin American populations.2%1

Vocabulary: Fitzpatrick skin type (fitzpatrick_1988)

Undertone

n = 64 assessable · 2 not assessable

Hue character of the skin independent of overall depth (Fitzpatrick). Reflects relative balance of hemoglobin (red), melanin (brown), and carotenoid (yellow) contributions to perceived color.

ValueSharen
warmYellow, peach, or golden cast. Veins on inner wrist appear greenish.70%45
neutralBalanced; neither warm nor cool dominant.2%1
coolPink, rosy, or bluish cast. Veins on inner wrist appear blue or purple.27%17
oliveGreenish-yellow cast; common in Mediterranean, Middle Eastern, and some South / Southeast Asian populations. Often grouped with warm in cosmetic shorthand but anatomically distinct.2%1

Vocabulary: Skin undertone (undertone_qualitative)

Where these numbers come from

66 publicly documented portraits of notable Welsh people were assessed by a vision model against the catalog vocabulary, one row per portrait. Values are what the photographs show, read by a model, not population measurements. Each table counts only portraits where the value could be assessed; covered, obscured and unclear portraits are reported separately.

Notable-people corpora skew older, so hair color over-represents gray and white, and image quality varies. Treat shares as a description of this sample. Mean model confidence for this family: 0.77. 55% of portraits are high quality.

The same rows are published as image_observations in the catalog dataset; see the methodology. A family page exists only when at least 10 portraits carry an assessable value.