The interpupillary distance (IPD) of a user’s face is used to frame prescription or non-prescription glasses, or other eyewear. The requirement for an IPD measurement necessitates a physical visit to an optometrist, making online glass (or frame) orders or virtual try-ons (VTO), difficult or infeasible. This disclosure leverages the near constancy of eyeball diameter across the human population to predict the IPD using geometric and/or machine learning techniques. The visible portion of the eyeball (the iris) is used to infer eyeball position. The eyeball position and a priori known size serve as reference dimensions to determine the IPD and/or dimensions of other facial features.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.