# US 2021/0334518 A1 · Method, device, apparatus and storage medium for facial matching > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0334518 A1 - Document ID: US20210334518A1 - Status: Published application - Kind: A1 - Application number: 16/488,704 - Filed: 2019-01-11 - Published: 2021-10-28 - Earliest claimed: 2018-05-25 - Assignees: BElJ!NG BOE OPTOELECTRONICS TECHNOLOGY CO., LTD.; Boe Technology Group Co., Ltd. - Applicants: BElJ!NG BOE OPTOELECTRONICS TECHNOLOGY CO., LTD.; Boe Technology Group Co., Ltd. - Inventors: Yanan ZHANG; HAO WU; Xiaoping ZHANG; Yangli ZHENG; Xiaobo XIE; Xingpan SUN; Baolei GUO; Lingguo WANG; Bin FAN; Siqi YIN; Hongxuan SUN; Yongqiang JIANG; Mengxing XU; Cai ZHENG; Xianfeng MAO; Zhenguo ZHOU - Web page: https://patentgrep.com/patent/US20210334518A1 ## CPC - G06V 40/172: {Classification, e.g. identification} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/254: {of classification results, e.g. of results related to same input data} - G06V 10/75: Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries - G06V 10/809: {of classification results, e.g. where the classifiers operate on the same input data} - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships} - G06V 40/50: Maintenance of biometric data or enrolment thereof - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The present disclosure provides a method, a device, an apparatus and storage medium for facial matching, wherein the method includes: acquiring an image to be matched; conducting matching for the image to be matched based on at least one of an original sample database and an associative sample database; and outputting a final matching result, wherein the original sample database includes an original sample image, and the associative sample database includes an associative sample image which is formed by adding an associative feature to the original sample image. Herein, obtaining the original sample database and the associative sample database comprises: acquiring the original sample image; obtaining the original sample database based on the original sample image; adding the associative feature to the original sample image in the original sample database and generating the associative sample image, to obtain the associative sample database. ## Claims ### Claim 1 A method for facial matching, comprising: acquiring an image to be matched; conducting matching for the image to be matched based on at least one of an original sample database and an associative sample database; and outputting a final matching result, wherein the original sample database includes an original sample image, and the associative sample database includes an associative sample image which is formed by adding an associative feature to the original sample image. ### Claim 2 (depends on 1) The method according to claim 1, wherein obtaining the original sample database and the associative sample database comprises: acquiring the original sample image; obtaining the original sample database based on the original sample image; adding the associative feature to the original sample image in the original sample database and generating the associative sample image, to obtain the associative sample database. ### Claim 3 (depends on 2) The method according to claim 2, wherein the associative feature comprises at least one of scene, glasses, accessory, clothing, hair style. ### Claim 4 (depends on 1) The method according to claim 1, further comprising: conducting matching for the image to be matched based on a feature sample database, the feature sample database including a feature sample image, wherein obtaining the feature sample database comprises: changing a local feature of the associative sample image in the associative sample database and generating the feature sample image, to obtain the feature sample database. ### Claim 5 (depends on 4) The method according to claim 4, wherein the changing a local feature of the associative sample database in the associative sample database comprises: removing the local feature in the associative sample image and/or changing at least one of a size and a shape of the local feature, wherein the local feature includes at least one of nevus, scar, beard, eyebrow shape, mouth, nose, eye, and ear. ### Claim 6 (depends on 1) The method according to claim 1, wherein conducting matching for the image to be matched comprises: matching the image to be matched with the original sample image in the original sample database, and determining a first matching result; generating a final matching result based on the first matching result if the first matching result is greater than or equal to a first threshold. ### Claim 7 (depends on 6) The method according to claim 6, wherein if the first matching result is smaller than the first threshold, conducting matching for the image to be matched further comprises: matching the image to be matched with the associative sample image in the associative sample database, and determining a second matching result; determining a third matching result based on the first matching result and the second matching result; generating the final matching result based on the third matching result if the third matching result is greater than or equal to a second threshold, wherein the second threshold is the same as or different from the first threshold. ### Claim 8 (depends on 7) The method according to claim 7, wherein determining the third matching result comprises: setting a first weight value for the first matching result; setting a second weight value for the second matching result; determining a third matching result based on a product of the first matching result and the first weight value and a product of the second matching result and the second weight value, wherein the first weight value is greater than the second weight value. ### Claim 9 (depends on 7) The method according to claim 7, wherein if the third matching result is smaller than the second threshold, conducting matching for the image to be matched further comprises: matching the image to be matched with the feature sample image in the feature sample database, and determining a fourth matching result; determining a fifth matching result based on the first matching result, the second matching result and the fourth matching result; generating the final matching result based on the fifth matching result if the fifth matching result is greater than or equal to the third threshold, wherein the third threshold is the same as or different from the second threshold. ### Claim 10 (depends on 9) The method according to claim 9, wherein the determining a fifth matching result comprises: setting a third weight value for the first matching value; setting a fourth weight value for the second matching value; setting a fifth weight value for the fourth matching value; determining the fifth matching result based on a product of the first matching result and the third weight value, a product of the second matching result and the fourth weight value, and a product of the fourth matching result and the fifth weight value, wherein the third weight value is greater than the fourth weight value, and the fifth weight value. ### Claim 11 (depends on 4) The method according to claim 4, further comprising updating at least one of the original sample database, the associative sample database, and the feature sample database based on the image to be matched. ### Claim 12 A device for facial recognition, comprising: an input module, configured to acquire an image to be matched; a weight analysis module, configured to conduct matching for the image to be matched based on at least one of an original sample database and an associative sample database; and an output module, configured to output a final analysis result, wherein the original sample database includes an original sample image, and the associative sample database includes an associative sample image which is formed by adding an associative feature to the original sample image. ### Claim 13 (depends on 12) The device according to claim 12, wherein the input module is further configured to acquire the original sample database, and the device further comprises: an algorithm processing module, configured to; obtain the original sample database based on the original sample image; add the associative feature to the original sample image in the original sample database and generate the associative sample image, to obtain the associative sample database; a sample database storage module, configured to store the sample database, wherein the associative feature comprises at least one of scene, glasses, accessory, clothing, hair style. ### Claim 14 (depends on 12) The device according to claim 12, wherein the weight analysis module is further configured to conduct matching of the image to be matched based on a feature sample database, wherein the algorithm processing module is further configured to: change a local feature of the associative sample image in the associative sample database and generate a feature sample image, to obtain the feature sample database, wherein the local feature includes at least one of nevus, scar, beard, eyebrow shape, mouth, nose, eye, and ear. ### Claim 15 (depends on 12) The device according to claim 12, wherein the weight analysis module is further configured to: match the image to be matched with the original sample image in the original sample database, and determine a first matching result; generate a final matching result based on the first matching result if the first matching result is greater than or equal to a first threshold. ### Claim 16 (depends on 15) The device according to claim 15, wherein if the first matching result is smaller than the first threshold, the weight analysis module is further configured to: match the image to be matched with the associative sample image in the associative sample database, and determine a second matching result; determine a third matching result based on the first matching result and the second matching result; generate the final matching result based on the third matching result if the third matching result is greater than or equal to a second threshold, wherein the second threshold is the same as or different from the first threshold, determining, by the weight analysis module, the third matching result comprises: setting a first weight value for the first matching result; setting a second weight value for the second matching result; determining a third matching result based on a product of the first matching result and the first weight value and a product of the second matching result and the second weight value, wherein the first weight value is greater than the second weight value. ### Claim 17 (depends on 16) The device according to claim 16, wherein if the third matching result is smaller than the second threshold, the weight analysis module is further configured to: match the image to be matched with the feature sample image in the feature sample database, and determine a fourth matching result; determine a fifth matching result based on the first matching result, the second matching result and the fourth matching result; generate the final matching result based on the fifth matching result if the fifth matching result is greater than or equal to the third threshold, wherein the third threshold is the same as or different from the second threshold, determining, by the weight analysis module, by the fifth matching result comprises: setting a third weight value for the first matching value; setting a fourth weight value for the second matching value; setting a fifth weight value for the fourth matching value; determining the fifth matching result based on a product of the first matching result and the third weight value, a product of the second matching result and the fourth weight value, and a product of the fourth matching result and the fifth weight value, wherein the third weight value is greater than the fourth weight value, and the fifth weight value. ### Claim 18 (depends on 14) The device according to claim 14, wherein the algorithm processing module is further configured to update at least one of the original sample database, the associative sample database, and the feature sample database based on the image to be matched. ### Claim 19 (depends on 1) An apparatus for facial matching, comprising: at least one processor; and at least one storage, wherein the storage is stored with computer readable code, wherein the computer readable code executes the method for facial matching according to claim 1 when being run by the at least one processor. ### Claim 20 (depends on 1) A non-transient computer readable storage medium in which computer readable code is stored, wherein the computer readable code executes the method for facial matching according to claim 1 when being run by one or more processors.