# US 9,519,825 B2 · Determining access permission > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,519,825 B2 - Document ID: US9519825B2 - Status: Granted - Kind: B2 - Application number: 14/674,092 - Filed: 2015-03-31 - Published: 2016-10-06 - Granted: 2016-12-13 - Earliest claimed: 2015-03-31 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Jin Sheng Gao; Jin Jun Su; Rong Sun - Web page: https://patentgrep.com/patent/US9519825B2 ## CPC - G06F 21/40: by quorum, i.e. whereby two or more security principals are required - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06V 40/173: {face re-identification, e.g. recognising unknown faces across different face tracks} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An access permission level for a first individual may be calculated by utilizing repositories of social network databases. The facial image of a first individual may be captured and compared with a repository of pre-categorized individuals. In response to the facial image of the first individual being absent from the repository of pre-categorized individuals, the repositories of social network databases may be crawled to collect facial images of non-categorized individuals. The first facial image may be compared with the facial images of non-categorized individuals, and a second individual may be identified. In response to identifying, categorization data associated with the second individual may be collected. Utilizing the categorization data, the second individual may be sorted into one of a plurality of categories. Based upon an image match score and the category which the second individual is sorted into, an access permission level may be determined and provided to a user. ## Claims ### Claim 1 A computer-implemented method for utilizing repositories of social network databases for calculating an access permission level for a first individual, comprising: receiving a first facial image of the first individual captured through a monitoring device at a computerized locking mechanism; comparing, in response to the receiving, the first facial image with facial images of pre-categorized individuals stored in a repository of pre-categorized individuals, wherein each pre-categorized individual is sorted into a category within a group of categories including at least a first category, a second category, and a third category; comparing, in response to the first facial image being absent from the repository of pre-categorized individuals, the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals; identifying, based on the comparing, a facial image of a second individual that has an image match score with the first facial image that is above an image match threshold; collecting, in response to the identifying, categorization data associated with the second individual from the repositories of social network databases; sorting, based on the collected categorization data, the second individual into one of the categories; determining, based on the image match score of the second individual and category of the second individual, an access permission level for the first individual; and providing the access permission level to a first user; wherein determining an access permission level includes accessing a security policy, wherein the security policy utilizes an identification value matrix to define access permission. ### Claim 2 (depends on 1) The method of claim 1, wherein comparing the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals further includes crawling, in response to the first facial image being absent from the repository of non-categorized individuals, the repositories of social network databases to collect facial images of non-categorized individuals. ### Claim 3 (depends on 1) The method of claim 1, wherein collecting categorization data includes accessing law enforcement databases and gathering information associated with image data. ### Claim 4 (depends on 1) The method of claim 1, wherein the access permission level includes a green indicator, a yellow indicator, and a red indicator. ### Claim 5 (depends on 1) The method of claim 1, wherein failing to locate a facial image includes comparing the first facial image of the first individual with the facial images in the first category, the second category, and the third category. ### Claim 6 (depends on 1) The method of claim 1, wherein the first category includes family members of the first user, the second category includes friends of family members of the first user, and the third category includes individuals unidentified relative to the first user. ### Claim 7 (depends on 1) The method of claim 1, wherein sorting the second individual includes implementing a geometric learning process to build a facial data model associated with the categorization data to be stored within the first category, the second category, or the third category. ### Claim 8 (depends on 1) The method of claim 1, wherein crawling repositories of social network databases includes accessing contact data provided by the first user. ### Claim 9 (depends on 1) The method of claim 1, wherein providing the access permission level further includes: receiving, at the monitoring device, the access permission level for the first individual in conjunction with the categorization data used to determine the image match score for the facial image of the second individual; and displaying the permission level and the categorization data used to determine the image match score for the facial image of the second individual to the first user through a graphical user interface within the monitoring device. ### Claim 10 (depends on 1) The method of claim 1, further comprising unlocking the computerized locking mechanism in response to generating the access permission level. ### Claim 11 (depends on 1) The method of claim 1, further including in response to the first facial image being absent from both the repository of pre-categorized individuals and the repository of non-categorized individuals, contacting a second user to identify the first individual. ### Claim 12 A computer program product for utilizing repositories of social network databases for calculating an access permission level for a first individual, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising: receiving a first facial image of the first individual captured through a monitoring device at a computerized locking mechanism; comparing, in response to the receiving, the first facial image with facial images of pre-categorized individuals stored in a repository of pre-categorized individuals, wherein each pre-categorized individual is sorted into a category within a group of categories including at least a first category, a second category, and a third category; comparing, in response to the first facial image being absent from the repository of pre-categorized individuals, the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals; identifying, based on the comparing, a facial image of a second individual that has an image match score with the first facial image that is above an image match threshold; collecting, in response to the identifying, categorization data associated with the second individual from the repositories of social network databases; sorting, based on the collected categorization data, the second individual into one of the categories; determining, based on the image match score of the second individual and category of the second individual, an access permission level for the first individual; and providing the access permission level to a first user; wherein determining an access permission level includes accessing a security policy, wherein the security policy utilizes an identification value matrix to define access permission. ### Claim 13 (depends on 12) The computer program product of claim 12, wherein comparing the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals further includes crawling, in response to the first facial image being absent from the repository of non-categorized individuals, the repositories of social network databases to collect facial images of non-categorized individuals. ### Claim 14 (depends on 12) The computer program product of claim 12, wherein collecting categorization data includes accessing law enforcement databases and gathering information associated with image data. ### Claim 15 A computer system for utilizing repositories of social network databases for calculating an access permission level for a first individual, the computer system comprising: a memory; and a processor in communication with the memory, wherein the processor is configured to perform a method, the method comprising: receiving a first facial image of the first individual captured through a monitoring device at a computerized locking mechanism; comparing, in response to the receiving, the first facial image with facial images of pre-categorized individuals stored in a repository of pre-categorized individuals, wherein each pre-categorized individual is sorted into a category within a group of categories including at least a first category, a second category, and a third category; comparing, in response to the first facial image being absent from the repository of pre-categorized individuals, the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals; identifying, based on the comparing, a facial image of a second individual that has an image match score with the first facial image that is above an image match threshold; collecting, in response to the identifying, categorization data associated with the second individual from the repositories of social network databases; sorting, based on the collected categorization data, the second individual into one of the categories; determining, based on the image match score of the second individual and category of the second individual, an access permission level for the first individual; and providing the access permission level to a first user; wherein determining an access permission level includes accessing a security policy, wherein the security policy utilizes an identification value matrix to define access permission. ### Claim 16 (depends on 15) The computer system of claim 15, wherein comparing the first facial image with facial images of non-categorized individuals stored in a repository of non-categorized individuals further includes crawling, in response to the first facial image being absent from the repository of non-categorized individuals, the repositories of social network databases to collect facial images of non-categorized individuals. ### Claim 17 (depends on 15) The computer system of claim 15, wherein sorting the second individual includes implementing a geometric learning process to build a facial data model associated with the categorization data to be stored within the first category, the second category, or the third category. ### Claim 18 (depends on 15) The computer system of claim 15, wherein providing the access permission level further includes: receiving, at the monitoring device, the access permission level for the first individual in conjunction with the categorization data used to determine the image match score for the facial image of the second individual; and displaying the permission level and the categorization data used to determine the image match score for the facial image of the second individual to the first user through a graphical user interface within the monitoring device.