# US 10,311,290 B1 · System and method for generating a facial model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,290 B1 - Document ID: US10311290B1 - Status: Granted - Kind: B1 - Application number: 15/498,827 - Filed: 2017-04-27 - Granted: 2019-06-04 - Earliest claimed: 2015-12-29 - Assignees: Rogue Capital LLC - Applicants: Rogue Capital LLC - Inventors: Gideon Littwin; Adi Eckhouse Barzilai - Web page: https://patentgrep.com/patent/US10311290B1 ## CPC - G06V 40/172: {Classification, e.g. identification} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/23: Clustering techniques - G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate - G06T 2207/30201: Face - G06V 40/179: {metadata assisted face recognition} - G06V 2201/10: Recognition assisted with metadata - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system and method for generation of a facial model. The method includes analyzing, via machine vision, a plurality of multimedia content elements to identify a plurality of facial images shown in the plurality of multimedia content elements; clustering the identified facial images into at least one cluster, wherein the clustering is based on metadata associated with each of the plurality of facial images; and selecting, from among the at least one cluster, a representative cluster representing a face, wherein the facial model is the selected representative cluster. ## Claims ### Claim 1 A method for generation of a facial model, comprising: analyzing a plurality of multimedia content elements to identify a plurality of facial images shown in the plurality of multimedia content elements; clustering the identified facial images into at least one cluster, wherein the clustering is based on metadata associated with each of the plurality of facial images; selecting, from among the at least one cluster, a representative cluster representing a face, wherein the facial model is the selected representative cluster; receiving a request to access a secure activity; capturing at least one additional multimedia content element in response to the request to access the secure activity; analyzing the at least one additional multimedia content element to identify at least one additional facial image; comparing the at least one additional facial image to the facial model; and selectively permitting access to the secure activity responsive to a result of the comparing of the at least one additional facial image to the facial model. ### Claim 2 (depends on 1) The method of claim 1, further comprising: generating, for each cluster, a score, wherein each score indicates a probability that the cluster represents the face, wherein the representative cluster is selected based on the generated at least one score. ### Claim 3 (depends on 2) The method of claim 2, further comprising: generating, for each identified facial image, a signature; and comparing the generated signatures, wherein the clustering is based on the comparison of the generated signatures. ### Claim 4 (depends on 3) The method of claim 3, wherein comparing the generated signatures further comprises: mapping a signature vector representation into vector space, wherein Euclidean distance is utilized as a first approximation. ### Claim 5 (depends on 4) The method of claim 4, further comprising: reducing a number of dimensions in the vector space. ### Claim 6 (depends on 3) The method of claim 3, further comprising: comparing each generated signature to a plurality of facial image signatures stored in a database; and determining, based on the comparison of each generated signature to the plurality of facial image signatures, at least one matching facial image of the identified plurality of facial images, wherein the representative cluster includes the determined at least one matching facial image. ### Claim 7 (depends on 1) The method of claim 1, wherein the metadata indicates whether a sensor that captured each of the plurality of multimedia content elements is a front facing sensor or a rear facing sensor. ### Claim 8 (depends on 1) The method of claim 1, further comprising: receiving, from a user device, a request to generate the facial model, wherein the request to generate the facial model includes the plurality of multimedia content elements. ### Claim 9 (depends on 1) The method of claim 1, further comprising: adaptively updating the generated facial model based on at least one new multimedia content element. ### Claim 10 A non-transitory computer readable medium having stored thereon instructions which, when executed by processing circuitry, cause the processing circuitry to perform a process, the process comprising: analyzing a plurality of multimedia content elements to identify a plurality of facial images shown in the plurality of multimedia content elements; clustering the identified facial images into at least one cluster, wherein the clustering is based on metadata associated with each of the plurality of facial images; selecting, from among the at least one cluster, a representative cluster representing a face, wherein the facial model is the selected representative cluster; receiving a request to access a secure activity; capturing at least one additional multimedia content element in response to the request to access the secure activity; analyzing the at least one additional multimedia content element to identify at least one additional facial image; comparing the at least one additional facial image to the facial model; and selectively permitting access to the secure activity responsive to a result of the comparing of the at least one additional facial image to the facial model. ### Claim 11 A system for generation of a facial model, comprising: processing circuitry; and a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to: analyze a plurality of multimedia content elements to identify a plurality of facial images shown in the plurality of multimedia content elements; cluster the identified facial images into at least one cluster, wherein the clustering is based on metadata associated with each of the plurality of facial images; select, from among the at least one cluster, a representative cluster representing a face, wherein the facial model is the selected representative cluster; receive a request to access a secure activity; capture at least one additional multimedia content element in response to the request to access the secure activity; analyze the at least one additional multimedia content element to identify at least one additional facial image; compare the at least one additional facial image to the facial model; and selectively permit access to the secure activity responsive to a result of the compare of the at least one additional facial image to the facial model. ### Claim 12 (depends on 11) The system of claim 11, wherein the system is further configured to: generate, for each cluster, a score, wherein each score indicates a probability that the cluster represents the face, wherein the representative cluster is selected based on the generated at least one score. ### Claim 13 (depends on 12) The system of claim 12, wherein the system is further configured to: generate, for each identified facial image, a signature; and compare the generated signatures, wherein the clustering is based on the comparison of the generated signatures. ### Claim 14 (depends on 13) The system of claim 13, wherein the system is further configured to: map a signature vector representation into vector space, wherein Euclidean distance is utilized as a first approximation. ### Claim 15 (depends on 14) The system of claim 14, wherein the system is further configured to: reduce a number of dimensions in the vector space. ### Claim 16 (depends on 13) The system of claim 13, wherein the system is further configured to: compare each generated signature to a plurality of facial image signatures stored in a database; and determine, based on the comparison of each generated signature to the plurality of facial image signatures, at least one matching facial image of the identified plurality of facial images, wherein the representative cluster includes the determined at least one matching facial image. ### Claim 17 (depends on 11) The system of claim 11, wherein the metadata indicates whether a sensor that captured each of the plurality of multimedia content elements is a front facing sensor or a rear facing sensor. ### Claim 18 (depends on 11) The system of claim 11, wherein the system is further configured to: receive, from a user device, a request to generate the facial model, wherein the request to generate the facial model includes the plurality of multimedia content elements. ### Claim 19 (depends on 11) The system of claim 11, wherein the system is further configured to: adaptively update the generated facial model based on at least one new multimedia content element.