System and method for fabricating a custom face mask

US12226959B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12226959-B2
Application numberUS-202117381871-A
CountryUS
Kind codeB2
Filing dateJul 21, 2021
Priority dateJul 21, 2020
Publication dateFeb 18, 2025
Grant dateFeb 18, 2025

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A system and method for fabricating a custom face mask. The system includes a factory client, wherein the factory client includes a computing device configured to receive, at a factory server and at least a user device, an image datum comprising a plurality of data of a face of a user. The computing device is further configured to map, as a function of a first machine-learning model, at least a facial landmark to a three-dimensional (3D) mesh of the image datum, map, as a function of a second machine-learning mode, a path to the 3D mesh including a boundary of a custom face mask configured for use on a user's face, generate a model file of a mold, instruct a manufacturing tool, and instruct a manufacturing device to thermoform the plastic component of the mold.

First claim

Opening claim text (preview).

What is claimed is: 1. A system for fabricating a custom face mask, the system comprising: a factory client, factory client comprising a computing device, the computing device configured to: receive, at a factory server, an image datum and at least a user device, the image datum comprising a plurality of data of a face of a user; map, as a function of a first machine-learning model, at least a facial landmark to a three-dimensional (3D) mesh of the image datum; map, as a function of a second machine-learning mode, a path to the 3D mesh, the path comprising a boundary of a custom face mask configured for use on a user's face, wherein the second machine-learning model is trained using training data, the training data comprising: a plurality of facial landmark examples; and a plurality of boundary examples; generate a mold model file, the mold model file comprising the custom face mask mesh, as a function of the path to the 3D mesh and the 3D mesh of the image datum from the first machine-learning model and second machine-learning model; generate a manufacturing instruction set as a function of the mold model file and the custom face mask mesh; instruct a manufacturing device, manufacturing device configured to create the mold as a function of the model file; and thermoform a plastic component as a function of the manufacturing device. 2. The system of claim 1 , wherein the custom face mask includes at least a filter and at least a filter housing. 3. The system of claim 1 , wherein the custom face mask includes a mask housing. 4. The system of claim 3 , wherein the mask housing configured to fit around the plastic component. 5. The system of claim 4 , wherein the mask housing and at least a filter housing is printed using at least a 3D printer. 6. The system of claim 4 , wherein the custom face mask further includes a strap connected to at least a strap hole in the mask housing. 7. The system of claim 1 , wherein the plastic component includes a transparent plastic component. 8. The system of claim 1 , wherein the plastic component includes a flexible plastic component. 9. The system of claim 1 , wherein the manufacturing device includes an automated manufacturing device. 10. The system of claim 1 , wherein the manufacturing device includes at least a thermoforming device. 11. A method for fabricating a custom face mask, the method comprising: receiving, at a factory server, an image datum, image datum comprising, a plurality of data of a face of a user; mapping, as a function of a first machine-learning model, at least a facial landmark to a three-dimensional (3D) mesh of the image datum; mapping, as a function of a second machine-learning mode, a path to the 3D mesh, the path comprising a boundary of a custom face mask configured for use on a user's face, wherein the second machine-learning model is trained using training data, the training data comprising: a plurality of facial landmark examples; and a plurality of boundary examples; generating a mold model file, the mold model file comprising a custom face mask mesh, as a function of the path to the 3D mesh and the 3D mesh of the image datum; generating a manufacturing instruction set as a function of the mold model file and the custom face mask mesh; and instructing a manufacturing device, manufacturing device configured to create the mold as a function of the model file. 12. The method of claim 11 , wherein the image datum includes a 3D scan point clout of a user's face. 13. The method of claim 12 , wherein the instructing the manufacturing device further includes instructing a computer numerical control machine (CNC), CNC configured to trim a plastic component from the mold. 14. The method of claim 13 , wherein trimming the plastic component from the mold comprises: extracting, by the factory server, a cutting curve from the mold file, the mold file configured to represent the boundary of the custom face mask on the model file; and instructing the CNC to trim the plastic component as a function of the cutting curve. 15. The method of claim 13 , wherein instructing CNC to trim the plastic component further includes trimming at least a filter hole from the plastic component, filter hole configured to avoid blocking at least the facial landmark. 16. The method of claim 11 , wherein the training data used to train the second machine-learning model for mapping the path to the 3D mesh further includes a plurality of 3D meshes of a plurality of faces from a plurality of users, wherein each 3D mesh includes at least a facial landmark mapped to the 3D mesh. 17. The method of claim 11 , wherein the mapping the path to the 3D mesh as a function of the second machine-learning model includes: retrieving, from a database, the plurality of 3D meshes of the plurality of faces, wherein the plurality of faces includes a distribution of at least a face shape and at least the facial landmarks; determining a path for the 3D meshes; mapping the path to each 3D mesh; and training the second machine learning model using at least the 3D meshes of the plurality of faces, at least the facial landmarks, and at least the mapped path to each 3D mesh. 18. The method of claim 11 , wherein the instructing the manufacturing device further includes thermoforming an edge of the plastic component to protrude outward from the mold, wherein the plastic component is flush with a face when used. 19. The method of claim 11 further comprising manufacturing a plastic component of the mold using the manufacturing device. 20. The method of claim 11 , wherein manufacturing further includes manufacturing a transparent plastic component.

Assignees

Inventors

Classifications

  • characterised by their shape · CPC title

  • involving 3D image data · CPC title

  • Masks · CPC title

  • Products made by additive manufacturing · CPC title

  • Masks (gas-masks for animals A62B18/06; masks for welders A61F9/06) · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12226959B2 cover?
A system and method for fabricating a custom face mask. The system includes a factory client, wherein the factory client includes a computing device configured to receive, at a factory server and at least a user device, an image datum comprising a plurality of data of a face of a user. The computing device is further configured to map, as a function of a first machine-learning model, at least a…
Who is the assignee on this patent?
Desprez Llc
What technology area does this patent fall under?
Primary CPC classification B33Y50/02. Mapped technology areas include Operations & Transport.
When was this patent published?
Publication date Tue Feb 18 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 2 related publications on this page (citations in our corpus or others sharing the same primary CPC).