# US 10,311,291 B2 · Face recognition method, device and computer readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,291 B2 - Document ID: US10311291B2 - Status: Granted - Kind: B2 - Application number: 15/512,453 - Filed: 2015-01-23 - Published: 2017-10-26 - Granted: 2019-06-04 - Earliest claimed: 2014-09-19 - Assignees: Zte Corporation - Applicants: Zte Corporation - Inventors: Xiaoliang Zhang; Lei Feng; Weishan Sun - Web page: https://patentgrep.com/patent/US10311291B2 ## CPC - G06V 40/172: {Classification, e.g. identification} - G06V 20/64: Three-dimensional [3D] objects - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/173: {face re-identification, e.g. recognising unknown faces across different face tracks} - G06V 2201/10: Recognition assisted with metadata - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A face recognition method, device and a computer-readable storage medium are provided. The face recognition method includes: capturing face images of a user at a plurality of preset positions respectively; storing the face images and the preset positions corresponding to the face images; determining, in face recognition, one of the preset positions where the image is to be captured, and capturing a current face image of the user at the determined preset position; searching a corresponding face image in a storage device according to the determined preset position; and determining whether the current face image is matched with the searched face image. ## Claims ### Claim 1 A face recognition method, comprising: determining an initial position where a terminal is located; capturing face images of a user at a plurality of preset positions of the terminal respectively; acquiring respective offset parameters of the terminal relative to the initial position at a time of capturing the face images at the plurality of preset positions, wherein the offset parameters are used to characterize the preset positions; storing the face images and the offset parameters corresponding to the face images; presenting, in face recognition, selectable preset positions to the user according to the stored offset parameters; determining, according to an instruction input by the user, the preset position where the face image of the user is to be captured; capturing a current face image of the user at the determined preset position; searching a corresponding stored face image according to the determined preset position; and determining whether the current face image is matched with the searched face image. ### Claim 2 (depends on 1) The face recognition method according to claim 1, further comprising the following steps if the current face image is not matched with the searched face image: searching a corresponding offset parameter in a storage device according to the determined preset position; obtaining, according to the offset parameter searched in the storage device and a current position of the terminal, the initial position where the terminal is located; acquiring a face image of the user directly when the face recognition is performed again; determining, according to the obtained initial position and the current position of the terminal, the preset position where the terminal is currently located at the time of capturing an image; searching a corresponding face image in the storage device according to the preset position, and determining whether the face image currently captured is matched with the searched face image. ### Claim 3 (depends on 2) The face recognition method according to claim 2, further comprising the following steps prior to capturing the images at the plurality of preset positions: establishing an initial coordinate system according to the initial position where the terminal is located; wherein the step of capturing face images of a user at a plurality of preset positions of the terminal respectively comprises: capturing the face images of the user at the plurality of preset positions of the terminal relative to the initial coordinate system, respectively; the step of acquiring offset parameters of the terminal relative to the initial position at a time of capturing the face images at the plurality of preset positions comprises: acquiring the offset parameters of the terminal relative to the initial coordinate system at the time of acquiring the face images at the plurality of preset positions; the step of obtaining, according to the offset parameter searched in the storage device and a current position of the terminal, the initial position where the terminal is located comprises: establishing a real-time coordinate system according to the current position of the terminal, and recovering the initial coordinate system according to the offset parameter searched in the storage device and the real-time coordinate system; the step of determining, according to the obtained initial position and the current position of the terminal, the preset position where the terminal is currently located at the time of acquiring an image comprises: determining, according to the recovered initial coordinate system and the current position of the terminal, the preset position where the terminal is currently located at the time of acquiring the image. ### Claim 4 (depends on 3) The face recognition method according to claim 3, both the initial coordinate system and the real-time coordinate system are three-dimensional spatial coordinate systems. ### Claim 5 (depends on 4) The face recognition method according to claim 4 wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 6 (depends on 2) The face recognition method according to claim 2 wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 7 (depends on 3) The face recognition method according to claim 3 wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 8 (depends on 1) The face recognition method according to claim 1 wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 9 (depends on 1) A non-statutory computer-readable storage medium storing a program instruction, wherein the program instruction, when being executed, can implement the method according to claim 1. ### Claim 10 A face recognition device, comprising a processor arranged to perform the steps in following modules: an image capturing module, a storage module, a matching module, a position determining module, an initial position determining module and a parameter acquiring module; wherein the image capturing module is arranged to capture face images of a user at a plurality of preset positions of a terminal, respectively, and acquire a current face image of the user at the preset position determined by the position determining module; the storage module is arranged to store the face images and offset parameters corresponding to the face images; the position determining module is arranged to present selectable preset positions to the user according to the stored offset parameters, and determine, according to an instruction input by the user, the preset position where the face image of the user is to be captured; the matching module is arranged to search a corresponding face image in the storage module according to the preset position determined by the position determining module, and determine whether the current face image is matched with the searched face image; the initial position determining module is arranged to, before the face images and the preset positions corresponding to the face images being stored by the storage module, determine an initial position where the terminal, to which the face recognition device is applied, is located; the parameter acquiring module is arranged to acquire respective offset parameters of the terminal relative to the initial position at a time of capturing the face images at the plurality of preset positions, wherein the offset parameters are used to characterize the preset positions. ### Claim 11 (depends on 10) The face recognition device according to claim 10, wherein the processor is further arranged to perform the steps in an initial position recovering module; the initial position recovering module is arranged to search a corresponding offset parameter in the storage module according to the determined preset position, and obtain, according to the offset parameter searched in the storage module and the current position of the terminal, the initial position where the terminal is located; the image capturing module is arranged to directly capture the face image of the user when the face recognition is performed again; and the position determining module is arranged to determine, according to the initial position obtained by the initial position recovering module and the current position of the terminal, the preset position where the terminal is currently located at the time of acquiring an image. ### Claim 12 (depends on 11) The face recognition device according to claim 11, wherein the processor is further arranged to perform the steps in a coordinate establishing module; wherein the coordinate establishing module is arranged to, prior to capturing the image by the image capturing module, establish an initial coordinate system according to the initial position where the terminal is located, and when the face recognition is performed again, establish a real-time coordinate system according to the current position of the terminal; the image capturing module is arranged to capture the face images of the user at the plurality of preset positions of the terminal relative to the initial coordinate system respectively; the parameter acquiring module is arranged to acquire the offset parameters of the terminal relative to the initial coordinate system at the time of capturing the face images at the plurality of preset positions; the initial position recovering module is arranged to recover the initial coordinate system according to the offset parameters searched in the storage module and the real-time coordinate system; and the position determining module is arranged to determine, according to the recovered initial coordinate system and the current position of the terminal, the preset position where the terminal is currently located at the time of acquiring the image. ### Claim 13 (depends on 12) The face recognition device according to claim 12, wherein both the initial coordinate system and the real-time coordinate system are three-dimensional spatial coordinate systems. ### Claim 14 (depends on 13) The face recognition device according to claim 13, wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 15 (depends on 11) The face recognition device according to claim 11, wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 16 (depends on 12) The face recognition device according to claim 12, wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 17 (depends on 10) The face recognition device according to claim 10, wherein the offset parameters comprise at least one of an offset angle and a displacement. ### Claim 18 (depends on 10) The face recognition device according to claim 10, wherein the offset parameters comprise at least one of an offset angle and a displacement.