The validity and practicality of sun-reactive skin types I through VI.

By T. Fitzpatrick. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Medical & Health AI

Citations in the corpus

Model Cards for Model Reporting (2018, background): “odels that provide benchmarked evaluation in a variety of conditions, such as across different cultural, demographic, or phenotypic groups (e.g., race, geographic location, sex, Fitzpatrick skin type [17]) and intersectional groups (e.g., age and race, or sex and Fitzpatrick skin type) that are rele”
Re-imagining Algorithmic Fairness in India and Beyond (2021, background): “often used by researchers as a phenotype [46], but was originally developed to categorise UV sensitivity) [73].”
Segment Anything (2023, methodology): “As MIAP does not contain perceived skin tone annotations, we use a proprietary dataset that contains annotations for the perceived Fitzpatrick skin type [36], which ranges from 1 (lightest skin tone) to 6 (darkest skin tone).”
Understanding and Evaluating Racial Biases in Image Captioning (2021, methodology): “1), we present workers with a person instance in a COCO image and ask them to provide the skin color using the Fitzpatrick Skin Type scale [25], ranging from 1 (lightest) to 6 (darkest), and the binary gender expression.”
Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy (2019, methodology): “Buolamwini and Gebru [10] adopt a binary gender classification and the Fitzpatrick skin type classification system [28].”
Diversity in Faces (2019, methodology): “Early studies used Fitzpatrick skin type (FST) to classify sun-reactive skin types [38], which was also adopted recently in [36].”
Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, background): “Recently, benchmarks quantifying discrimination (Kilbertus et al. 2017; Hardt et al. 2016) and even datasets designed to evaluate the fairness of these algorithms (Buolamwini and Gebru 2018) have emerged.”
Accuracy in Wrist-Worn, Sensor-Based Measurements of Heart Rate and Energy Expenditure in a Diverse Cohort (2016, unknown): “Skin tone at the wrist was rated independently by two investigators using the Von Luschan Chromatic scale (1–36), and the average rating was then transformed to the Fitzpatrick skin tone scale (1–6) [11].”
Towards causal benchmarking of bias in face analysis algorithms (2020, methodology): “For example, we use the Fitzpatrick sixpoint scale for skin color [23], and split age into six groups ranging from children to senior citizens.”
Diversity and Inclusion Metrics in Subset Selection (2020, background): “set that was diverse but not inclusive (D+I-), inclusive but not diverse (D-I+), both inclusive and diverse (D+I+), and neither inclusive nor diverse (D-I-). 3skin:6 refers to Fitzpatrick Skin Type 6 [16]. 4That is, all images are equally relevant to the query. Respondents were presented with pairs ”
Understanding Unequal Gender Classification Accuracy from Face Images (2018, background): “…Buolamwini and Gebru created a dataset of parliament members from three European and three African countries — the Pilot Parliaments Benchmark (PPB), balanced across two attributes: gender and Fitzpatrick skin type [14], and evaluated the accuracy of three commercial facial gender classiﬁers [4].”
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets (2020, background): “Skin tone labels: Our skin tone annotations for COCO come from (D. Zhao et al., 2021), and are numbered 1-6 according to the Fitzpatrick scale (Fitzpatrick, 1988), where 1 is the lightest and 6 is the darkest.”
Design of an Active Multispectral SWIR Camera System for Skin Detection and Face Verification (2016, methodology): “…intensities of human skin in the visual and infrared spectral range up to 1700 nm for six different skin types, denoted as skin types 1 (very light colored) to 6 (very dark colored) after Fitzpatrick [11], compared to the remission spectra of materials that might be used to create facial disguises.”
Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks (2019, methodology): “With respect to skin type, participants in our data collection were in the range of II-IV on the Fitzpatrick scale (which ranges I-VI, where lower numbers refer to lighter skin [39]).”
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (2018, methodology): “We chose the Fitzpatrick six-point labeling system to determine skin type labels given its scientiﬁc origins.”
Meta-analysis of risk factors for cutaneous melanoma: III. Family history, actinic damage and phenotypic factors. (2005, background): “This classification of skin type into four categories, from type I (always burn, never tan) to type IV (never burn, tan easily), is widely used clinically, although the precise questions asked and the responses coded vary between studies [5].”
Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias (2019, methodology): “[4, 34] compare error statistics of facial analysis systems across groups de-ﬁned by Fitzpatrick skin type [9] and gender; while [22] compares across groups deﬁned by race/ethnicity, age and gender, as categorized by Florida police records.”
The Evolution of Human Skin and Skin Color (2004, background): “…has been classified commonly according to skin phototypes or sun-reactive skin types, from Type I (very sensitive, easily burned, with little or no potential for tanning) to Type VI (insensitive, never burns, and deeply pigmented) (Fitzpatrick 1988, Fitzpatrick & Ortonne 2003, Jimbow et al. 1991).”
The Protective Role of Melanin Against UV Damage in Human Skin † (2008, background): “The concept of skin phototype was originally created to optimize UVR doses in phototherapy (98).”