# US 11,443,460 B2 · Dynamic mask application > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,460 B2 - Document ID: US11443460B2 - Status: Granted - Kind: B2 - Application number: 16/809,868 - Filed: 2020-03-05 - Published: 2020-06-25 - Granted: 2022-09-13 - Earliest claimed: 2016-12-22 - Assignees: Meta Platforms, Inc. - Applicants: Meta Platforms, Inc. - Inventors: Maria Luz Caballero; Molly Jane Fowler; Congxi Lu; Charles Joseph Hodgkins; Daniel Alberto Cuellar - Web page: https://patentgrep.com/patent/US11443460B2 ## CPC - G06T 11/00: Two-dimensional [2D] image generation - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/174: {Facial expression recognition} - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract In one embodiment, a method includes identifying a first user in an input image, accessing social data of the first user in the input image, where social data comprises information from a social graph of an online social network, selecting, based on social data of the first user in the input image, a mask from a set of masks, where the mask specifies one or more mask effects, and for each of the input images, applying the mask to the input image. The set of masks may comprise masks previously selected by friends of the first user within the online social network. The selected mask may be selected from a lookup table that maps the social data to the selected mask. ## Claims ### Claim 1 A method comprising, by one or more computing devices: identifying a first user in an input image; identifying a facial expression of the first user in the input image, wherein identifying a facial expression comprises identifying an emotion; accessing social data of the first user in the input image, wherein the social data comprises information from a social graph of an online social network; determining a theme associated with masks previously used by the user; selecting a mask from a plurality of masks, wherein the plurality of masks comprise masks stored in a database and corresponding to a mapping table, the mapping table associating the identified emotion with one or more masks of the plurality of masks, the plurality of masks being indicated by the social data as being previously selected by friends of the first user within the online social network, and wherein selecting a mask from the plurality of masks is based on the social data of the first user and the determined theme associated with the masks previously used by the user and the identified emotion of the first user in the input image, wherein the mask specifies one or more mask effects; and applying the selected mask to the first user in the input image. ### Claim 2 (depends on 1) The method of claim 1, wherein the selected mask is selected from a lookup table that maps the social data to the selected mask. ### Claim 3 (depends on 1) The method of claim 1, wherein the identified expression is associated with the mask, and the mask is selected when the identified expression corresponds to at least one of the expressions associated with the mask. ### Claim 4 (depends on 1) The method of claim 1, wherein the mask is selected from the plurality of masks when a selection condition associated with the mask is satisfied by the social data of the user. ### Claim 5 (depends on 4) The method of claim 4, wherein the selection condition is satisfied when, for an attribute associated with the social data, a value of the attribute associated with the mask matches a value of the attribute associated with the user. ### Claim 6 (depends on 1) The method of claim 1, wherein applying the mask comprises generating one or more graphical features, wherein the mask effects include a mask image, and wherein the one or more graphical features are incorporated into an output image including one or more features from the mask image. ### Claim 7 (depends on 6) The method of claim 6, wherein the one or more features from the mask image are scaled based on a size of the first user in the input image. ### Claim 8 (depends on 6) The method of claim 6, wherein the one or more features from the mask image are positioned in the output image at locations that are determined based on locations of corresponding features of the input image according to mask geometry information associated with the mask effects. ### Claim 9 (depends on 1) The method of claim 1, further comprising: transforming the mask by modifying one or more graphical features to reflect one or more changes in one or more features of the first user in a second image successive to the first image. ### Claim 10 (depends on 1) The method of claim 1, wherein the graphical features generated by the mask effects comprise one or more of: exaggerated facial features, renderings of inanimate physical objects, or stylized facial features. ### Claim 11 (depends on 1) The method of claim 1, wherein the input image is captured using a camera. ### Claim 12 (depends on 1) The method of claim 1, wherein the input image is a photograph. ### Claim 13 (depends on 1) The method of claim 1, wherein the input image is a video. ### Claim 14 (depends on 1) The method of claim 1, further comprising: determining a geographic location associated with the input image, wherein selecting the mask from the plurality of masks is further based on the geographic location. ### Claim 15 (depends on 1) The method of claim 1, wherein the social data comprises information related to the first user stored within an online social network. ### Claim 16 (depends on 1) The method of claim 1, wherein the social data comprises one or more of a user profile, user interests, user preferences, user relationships on a social network, or location data. ### Claim 17 (depends on 1) The method of claim 1, wherein the social data comprises attributes related to the first user through nodes and edges of a social graph database. ### Claim 18 One or more computer-readable non-transitory storage media embodying software that is operable when executed to: identify a first user in an input image; identify a facial expression of the first user in the input image, wherein identifying a facial expression comprises identifying an emotion; access social data of the first user in the input image, wherein the social data comprises information from a social graph of an online social network; determine a theme associated with masks previously used by the user; select, based on the social data of the first user, a mask from a plurality of masks, wherein the plurality of masks comprise masks stored in a database and corresponding to a mapping table, the mapping table associating the identified emotion with one or more masks of the plurality of masks, the plurality of masks being indicated by the social data as being previously selected by friends of the first user within the online social network, and wherein selecting a mask from the plurality of masks is based on the social data of the first user and the determined theme associated with the masks previously used by the user and the identified emotion of the first user in the input image, wherein the mask specifies one or more mask effects; and apply the selected mask to the first user in the input image. ### Claim 19 A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to: identify a first user in an input image; identify a facial expression of the first user in the input image, wherein identifying a facial expression comprises identifying an emotion; access social data of the first user in the input image, wherein the social data comprises information from a social graph of an online social network; determine a theme associated with masks previously used by the user; select, based on the social data of the first user, a mask from a plurality of masks, wherein the plurality of masks comprise masks stored in a database and corresponding to a mapping table, the mapping table associating the identified emotion with one or more masks of the plurality of masks, the plurality of masks being indicated by the social data as being previously selected by friends of the first user within the online social network, and wherein selecting a mask from the plurality of masks is based on the social data and the determined theme associated with the masks previously used by the user and the identified emotion of the first user in the input image, wherein the mask specifies one or more mask effects; and apply the selected mask to the first user in the input image. ### Claim 20 (depends on 19) The system of claim 19, wherein identifying an emotion comprises determining one or more emotions associated with the identified facial expression.