{
  "id": 16185363,
  "title": "The skin tone scale that scores 16.67% on an arm",
  "url": "https://urgent.news/2026/10/23/the-skin-tone-scale-that-scores-16-67-on-an-arm",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-23T12:40:22.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/chuksadirije/the-skin-tone-scale-that-scores-1667-on-an-arm-28c0"
  },
  "original_language": "en",
  "account": "A research team attempted to automatically categorize skin tone by using an algorithm to estimate skin tone from color values measured in an arm photograph. They compared two scales - Fitzpatrick and Monk Skin Tone - and found that the Fitzpatrick scale only achieved 16.67% accuracy, while the Monk scale achieved 65.67% accuracy. The Fitzpatrick scale is based on a patient's response to UV exposure and is not a reliable measure of skin color, as two people with the same skin color can give different Fitzpatrick scores. The Monk scale, on the other hand, measures apparent skin tone and has ten points rather than six. It was designed with computer vision in mind and is not evenly spaced. The researchers found that trying to measure skin tone from pixels in phone photographs is unreliable because the camera automatically adjusts the exposure to the face in the frame, normalizing away the exact quantity being measured. The study highlights the importance of using a reliable scale like Monk Skin Tone for measuring skin tone, especially in consumer products where cameras may not provide a clear picture of the skin tone.",
  "summary": "If you build anything that reasons about skin, you almost certainly sort people onto the Fitzpatrick scale. A research team tried to do that automatically last year and scored 16.67% on a photograph of an arm. The same team, on the same images, scored 65.67% on those arms when they expressed the answer on a different scale. What the study found A group at TU Munich built an algorithm that…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}