BodySegmentation Model Card

The ml5.js BodySegmentation provides two models, SelfieSegmentation and BodyPix:

SelfieSegmentation

MediaPipe Selfie Segmentation Model Card

• Date created: 2021
• Size: Not stated
• How the data was collected: “This model was trained and evaluated on images, including consented images of people using a mobile AR application captured with smartphone cameras in various “in-the-wild” conditions.”
• Bias:
  • Categories of evaluation:
    • 17 demographical subregions
    • 6 skin tones
    • Male / Female (gender)
  • Evalutation results:
    • Subregions: Difference in confidence between average and worst performing regions of 1.11% for the general model, and 1.28% for the landscape model, lower than the criteria.
    • Gender: Differences in confidence are 1.6% for the general model and 0.6% for the landscape model.
    • Skin tone: Difference in confidence between worst and best performing

BodyPix

This short article is the only information on BodyPix that we have found.

Please submit any feedback/information you belive would be useful regarding this model here.