# US 10,769,490 B2 · Image processing methods and devices > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,490 B2 - Document ID: US10769490B2 - Status: Granted - Kind: B2 - Application number: 16/777,696 - Filed: 2020-01-30 - Published: 2020-05-28 - Granted: 2020-09-08 - Earliest claimed: 2017-07-20 - Assignees: Alibaba Group Holding Limited - Applicants: Alibaba Group Holding Limited - Inventors: Nan Jiang; Mingyu Guo - Web page: https://patentgrep.com/patent/US10769490B2 ## CPC - G06V 40/172: {Classification, e.g. identification} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/40: Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor - G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for image processing includes: acquiring features of multiple images of a target object and a standard feature of the target object; and determining trusted images of the target object from the multiple images of the target object according to similarities between the features of the multiple images of the target object and the standard feature thereof, wherein similarities between features of the trusted images of the target object and the standard feature of the target object meet a preset similarity requirement. The image processing method may be applied to application scenarios such as image comparison, identity recognition, target object search, and similar target object determination. ## Claims ### Claim 1 An image processing method, comprising: acquiring features of multiple images of a first target object and a standard feature of the first target object; determining trusted images of the first target object from the multiple images according to similarities between the features of the multiple images and the standard feature, wherein similarities between features of the trusted images and the standard feature meet a first preset similarity requirement; determining similarities between the trusted images of the first target object and trusted images of a second target object to obtain multiple pieces of similarity data; and determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object. ### Claim 2 (depends on 1) The method of claim 1, wherein the acquiring the standard feature of the first target object comprises one of: acquiring an average feature of the multiple images, and determining the average feature of the multiple images as the standard feature of the first target object; or acquiring an average feature of the multiple images, and determining a feature in the features of the multiple images as the standard feature of the first target object, wherein the determined feature is most similar to the average feature. ### Claim 3 (depends on 1) The method of claim 1, wherein the determining the trusted images of the first target object from the multiple images according to the similarities between the features of the multiple images and the standard feature comprises one of: determining one or more images of the multiple images as the trusted images of the first target object, wherein similarities between features of the one or more images of the multiple images and the standard feature are greater than or equal to a preset similarity threshold; or determining distribution data of the similarities between the features of the multiple images and the standard feature, determining a similarity interval in the distribution data, wherein an image density in the similarity interval is greater than or equal to a preset density, and determining one or more images of the multiple images corresponding to the determined similarity interval as the trusted images of the first target object. ### Claim 4 (depends on 1) The method of claim 1, wherein the determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object comprises one of: determining that the first target object is similar to the second target object when an average value of the multiple pieces of similarity data is greater than or equal to a preset average threshold; or determining that the first target object is similar to the second target object when a distribution of the multiple pieces of similarity data meets a preset similarity distribution requirement. ### Claim 5 (depends on 1) The method of claim 1, wherein the determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object comprises: determining whether a quantity of the multiple pieces of similarity data meets a preset quantity requirement; and when the quantity of the multiple pieces of similarity data meets the preset quantity requirement, determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object. ### Claim 6 (depends on 1) The method of claim 1, wherein the trusted images of the second target object are determined from multiple images of the second target object, and similarities between features of the trusted images of the second target object and a standard feature of the second target object meet a second preset similarity requirement. ### Claim 7 (depends on 6) The method of claim 6, wherein the standard feature of the first target object is one of an average feature of the multiple images of the first target object, or a feature in features of the multiple images of the first target object that is most similar to the average feature of the multiple images of the first target object; and the standard feature of the second target object is one of an average feature of the multiple images of the second target object, or a feature in features of the multiple images of the second target object that is most similar to the average feature of the multiple images of the second target object. ### Claim 8 (depends on 6) The method of claim 6, wherein the determining whether the first target object is similar to the second target object comprises one of: determining that the first target object is similar to the second target object when an average value of multiple pieces of similarity data between the trusted images of the first target object and the trusted images of the second target object is greater than or equal to a preset average threshold; or determining that the first target object is similar to the second target object when a distribution of multiple pieces of similarity data between the trusted images of the first target object and the trusted images of the second target object meets a preset similarity distribution requirement. ### Claim 9 (depends on 6) The method of claim 6, wherein the first target object is a first target object in a database of target objects, and the second target object is a second target object in the database, wherein the first target object is different from the second target object; or the first target object is a target object specified by a user, and the second target object is a target object in the database. ### Claim 10 (depends on 1) The method of claim 1, further comprising: acquiring features of multiple images of the second target object and a standard feature of the second target object; determining the trusted images of the second target object from the multiple images of the second target object according to similarities between the features of the multiple images of the second target object and the standard feature of the second target object, wherein similarities between features of the trusted images of the second target object and the standard feature of the second target object meet a second preset similarity requirement. ### Claim 11 (depends on 10) The method of claim 10, wherein the first preset similarity requirement is the same as the second preset similarity requirement, or the first preset similarity requirement is different from the second preset similarity requirement. ### Claim 12 An image processing device, comprising: a processor; and a memory storing a computer executable instruction, wherein when executed, the executable instruction causes the processor to: acquire features of multiple images of a first target object and a standard feature of the first target object; determine trusted images of the first target object from the multiple images according to similarities between the features of the multiple images and the standard feature, wherein similarities between features of the trusted images and the standard feature meet a first preset similarity requirement; determine similarities between the trusted images of the first target object and trusted images of a second target object to obtain multiple pieces of similarity data; and determine, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object. ### Claim 13 (depends on 12) The image processing device of claim 12, wherein the trusted images of the second target object are determined from multiple images of the second target object, and similarities between features of the trusted images of the second target object and a standard feature of the second target object meet a second preset similarity requirement. ### Claim 14 (depends on 12) The image processing device of claim 12, wherein when executed, the executable instruction further causes the processor to: acquire features of multiple images of the second target object and a standard feature of the second target object; and determine the trusted images of the second target object from the multiple images of the second target object according to similarities between the features of the multiple images of the second target object and the standard feature of the second target object, wherein similarities between features of the trusted images of the second target object and the standard feature of the second target object meet a second preset similarity requirement. ### Claim 15 A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processor of a device, cause the device perform an image processing method, the method comprising: acquiring features of multiple images of a first target object and a standard feature of the first target object; determining trusted images of the first target object from the multiple images according to similarities between the features of the multiple images and the standard feature, wherein similarities between features of the trusted images and the standard feature meet a first preset similarity requirement; determining similarities between the trusted images of the first target object and trusted images of a second target object to obtain multiple pieces of similarity data; and determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the trusted images of the second target object are determined from multiple images of the second target object, and similarities between features of the trusted images of the second target object and a standard feature of the second target object meet a second preset similarity requirement. ### Claim 17 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the method further comprises: acquiring features of multiple images of the second target object and a standard feature of the second target object; and determining the trusted images of the second target object from the multiple images of the second target object according to similarities between the features of the multiple images of the second target object and the standard feature of the second target object, wherein similarities between features of the trusted images of the second target object and the standard feature of the second target object meet a second preset similarity requirement.