Predicting sizing and/or fitting of head mounted wearable device
AssigneeGoogle Inc.
InventorsIdris Syed Aleem, Mayank Bhargava, Sushant Umesh Kulkarni, Ahmed Gawish, Rees Anwyl Samuel Simmons
Life of this patent
Estimating the term…
Abstract
A system and method of predicting the fitting of a head mounted wearable device for a user is provided. The system detects fixed facial landmarks in image data captured by a computing device of the user. Measurements associated with the detected fixed facial landmarks may be processed by one or more machine learning models and associated algorithm(s) to predict the probability of fitting of a head mounted wearable device on the head of the user.
Claims18
A computer-implemented method, comprising:
- capturing, via an application executing on a computing device operated by a user, image data including a head of the user;
- associating a fit parameter with a distance between two landmarks detected in the image data;
- calculating a measurement associated with the fit parameter, including applying a scale value to the distance between the two landmarks in the image data;
- and
- predicting, using at least one machine learning model, a probability of fitting a wearable device for the user based on the measurement associated with the fit parameter;
- wherein the at least one machine learning model is based on indicators of wearable fit of a plurality of differently configured wearable devices for a plurality of different measurements associated with the fit parameter.
A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a computing device are configured to cause the at least one processor to:
- capture, via an application executing on the computing device, image data including a head of a user;
- detect two landmarks in the image data;
- associate a fit parameter with a distance between the two landmarks in the image data;
- calculate a measurement associated with the fit parameter, including applying a scale value to the distance between the two landmarks in the image data;
- and
- predict, using at least one machine learning model, a probability of fitting of a wearable device for the user based on the measurement associated with the fit parameter;
- wherein the at least one machine learning model is based on indicators of wearable fit of a plurality of differently configured wearable devices for a plurality of different measurements associated with the fit parameter.
A system, comprising:
- a computing device, including:
- an image sensor;
- at least one processor;
- and
- a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to:
- capture, via an application executing on the computing device, image data including a head of a user of the computing device;
- detect two landmarks in the image data;
- associate a fit parameter with a distance between the two landmarks in the image data;
- calculate a measurement associated with the fit parameter, including applying a scale value to the distance between the two landmarks;
- and
- predict, using at least one machine learning model, a probability of fitting of a wearable device on the head of the user based on the measurement associated with the fit parameter;
- wherein the at least one machine learning model is based on indicators of wearable fit of a plurality of differently configured wearable devices for a plurality of different measurements associated with the fit parameter.
Dependencies are inferred from the claim text.