# US 2023/0410355 A1 · Predicting sizing and/or fitting of head mounted wearable device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0410355 A1 - Document ID: US20230410355A1 - Status: Published application - Kind: A1 - Application number: 17/807,230 - Filed: 2022-06-16 - Published: 2023-12-21 - Earliest claimed: 2022-06-16 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Idris Syed Aleem; Mayank Bhargava; Sushant Umesh Kulkarni; Ahmed Gawish; Rees Anwyl Samuel Simmons - Web page: https://patentgrep.com/patent/US20230410355A1 ## CPC - G02C 13/003: {Measuring during assembly or fitting of spectacles} - G02C 7/027: {considering wearer's parameters} - G02C 13/005: {Measuring geometric parameters required to locate ophtalmic lenses in spectacles frames (apparatus for testing or instruments for examining the eyes per se A61B3/00; machines or devices and accessories for grinding the edges of lenses using spectacles as a template B24B9/144)} - G06T 7/60: Analysis of geometric attributes - G06V 40/165: {using facial parts and geometric relationships} - G06T 2207/20076: Probabilistic image processing - G06T 2207/20081: Training; Learning - G06T 2207/30201: Face - G02C: SPECTACLES; SUNGLASSES OR GOGGLES INSOFAR AS THEY HAVE THE SAME FEATURES AS SPECTACLES; CONTACT LENSES (trial frames for testing the eyes A61B3/04; goggles or eyeshields not having the same features as spectacles A61F9/00) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## 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. ## Claims ### Claim 1 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; applying a scale value to a distance between two fixed landmarks detected in the image data; associating a measurement with the distance between the two fixed landmarks based on the scale value; and predicting, using at least one machine learning model, a probability of fitting a head mounted wearable device on the head of the user based on the measurement associated with the two fixed landmarks. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: detecting the two fixed landmarks in the image data from amongst a plurality of facial landmarks in the image data; and detecting a fit parameter based on a relative position the two fixed landmarks. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein associating the measurement with the distance between the two fixed landmarks includes determining a measurement associated with the fit parameter, the measurement associated with the fit parameter corresponding to the measurement associated with the distance between the two fixed landmarks. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein predicting the probability of the fitting of the head mounted wearable device on the head of the user includes: accessing, by the at least one machine learning model, fit scoring data associated with the head mounted wearable device; and determining the probability of fitting based on the fit scoring data and the measurement associated with the fit parameter. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein the fit scoring data includes numerical scores of wearable fit of a plurality of differently configured head mounted wearable devices for a plurality of different measurements associated with the fit parameter. ### Claim 6 (depends on 4) The computer-implemented method of claim 4, wherein the fit scoring data includes numerical scores of wearable fit of the head mounted wearable device across a plurality of different head width measurements. ### Claim 7 (depends on 3) The computer-implemented method of claim 3, wherein determining the measurement associated with the fit parameter includes determining at least one of a head width measurement, an inter-lateral commissure distance measurement, or an inter-medial commissure distance measurement based on the plurality of facial landmarks detected in the image data. ### Claim 8 (depends on 3) The computer-implemented method of claim 3, wherein determining the measurement associated with the fit parameter includes: determining a distance between any two of the plurality of facial landmarks having a static distance therebetween; and associating a measurement with the distance between the any two of the plurality of facial landmarks. ### Claim 9 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; apply a scale value to a distance between two fixed landmarks detected in the image data; associate a measurement with the distance between the two fixed landmarks based on the scale value; and predict, using at least one machine learning model, a probability of fitting of a head mounted wearable device on the head of the user based on the measurement associated with the two fixed landmarks. ### Claim 10 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the instructions cause the at least one processor to: detect the two fixed landmarks in the image data from amongst a plurality of facial landmarks in the image data; and detect a fit parameter based on a relative position of the two fixed landmarks. ### Claim 11 (depends on 10) The non-transitory computer-readable medium of claim 10, wherein the instructions cause the at least one processor to: determine a measurement associated with the fit parameter, the measurement associated with the fit parameter corresponding to the measurement associated with the distance between the two fixed landmarks. ### Claim 12 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions cause the at least one processor to: access, by the at least one machine learning model, fit scoring data associated with the head mounted wearable device; and determine the probability of fitting based on the fit scoring data and the measurement associated with the fit parameter. ### Claim 13 (depends on 12) The non-transitory computer-readable medium of claim 12, wherein the fit scoring data includes numerical scores of wearable fit of a plurality of differently configured head mounted wearable devices for a plurality of different measurements associated with the fit parameter. ### Claim 14 (depends on 12) The non-transitory computer-readable medium of claim 12, wherein the fit scoring data includes numerical scores of wearable fit of the head mounted wearable device across a plurality of different head width measurements. ### Claim 15 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions cause the at least one processor to: determine at least one of a head width measurement, an inter-lateral commissure distance measurement, or an inter-medial commissure distance measurement based on the plurality of facial landmarks detected in the image data. ### Claim 16 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions cause the at least one processor to: determine a distance between any two of the plurality of facial landmarks having a static distance therebetween; and associate a measurement with the distance between the any two of the plurality of facial landmarks. ### Claim 17 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; apply a scale value to a distance between two fixed landmarks detected in the image data; associate a measurement with the distance between the two fixed landmarks based on the scale value; and predict, using at least one machine learning model, a probability of fitting of a head mounted wearable device on the head of the user based on the measurement associated with the distance between the two fixed landmarks. ### Claim 18 (depends on 17) The system of claim 17, wherein the instructions cause the at least one processor to: detect the two fixed landmarks in the image data from amongst a plurality of facial landmarks in the image data; detect a fit parameter based on a relative position of the two fixed landmarks; and determine a measurement associated with the fit parameter, the measurement associated with the fit parameter corresponding to the measurement associated with the distance between the two fixed landmarks. ### Claim 19 (depends on 18) The system of claim 18, wherein the instructions cause the at least one processor to: access, by the at least one machine learning model, fit scoring data associated with the head mounted wearable device; and determine the probability of fit based on the fit scoring data and the measurement associated with the fit parameter. ### Claim 20 (depends on 19) The system of claim 19, wherein the fit scoring data includes numerical scores of wearable fit of a plurality of differently configured head mounted wearable devices for a plurality of different measurements associated with the fit parameter. ### Claim 21 (depends on 18) The system of claim 18, wherein the instructions cause the at least one processor to: determine a distance between any two of the plurality of facial landmarks having a static distance therebetween; and associate a measurement with the distance between the any two of the plurality of facial landmarks.