# US 10,872,416 B2 · Object oriented image editing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,416 B2 - Document ID: US10872416B2 - Status: Granted - Kind: B2 - Application number: 16/266,609 - Filed: 2019-02-04 - Published: 2019-08-01 - Granted: 2020-12-22 - Earliest claimed: 2015-02-19 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Peter Joseph McNerney; Nolan Andrew Miller - Web page: https://patentgrep.com/patent/US10872416B2 ## CPC - G06T 11/60: Creating or editing images; Combining images with text - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/24: Classification techniques - G06T 7/11: Region-based segmentation - G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06T 2207/20012: Locally adaptive - G06T 2207/20104: Interactive definition of region of interest [ROI] - G06T 2207/30201: Face - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Implementations generally relate to object based image editing. In some implementations, a method includes segmenting an image into object data by identifying one or more object classifications in the image and storing at least one locator for one or more regions of the image corresponding to each instance of the object classification. The method further includes receiving a selection of a representative portion of the segmented image from a user, and matching the representative portion with the object data to determine at least one matched object classification associated with the representative portion. The method further includes presenting the user with one or more of the matched object classifications for the user to instruct one or more edit operations to be applied to at least one object represented by the matched object classification. ## Claims ### Claim 1 A computer implemented method to edit an image, the method comprising: segmenting a first image into regions depicting objects; identifying two or more different classifications descriptive of respective objects of the objects in the first image; identifying at least one subcategory for a respective classification of the two or more different classifications, wherein the at least one subcategory has a greater level of specificity than a specificity of the respective classification and the at least one subcategory is represented by a respective semantic term; storing locator information for regions of the first image corresponding to the respective objects associated with the at least one subcategory; providing to a user device, the respective semantic term of the at least one subcategory; receiving a user selection of at least one semantic term indicating a select subcategory of the at least one subcategory; receiving a user request to apply one or more edit operations to at least one instance of an object in the first image associated with the select subcategory; and applying the one or more edit operations to the at least one instance of the object in the first image associated with the select subcategory by locating the at least one instance of the object with the location information for the at least one instance of the object. ### Claim 2 (depends on 1) The computer implemented method of claim 1, further including identifying a generic classification of a region of the first image. ### Claim 3 (depends on 1) The method of claim 1, wherein the at least one subcategory includes at least one of a gender, an age, or an identification name of a person classification. ### Claim 4 (depends on 1) The method of claim 1, wherein the select subcategory includes more than one instance of the object associated with the select subcategory and the user selection includes a select number of the instances of the object associated with the select subcategory. ### Claim 5 (depends on 1) The method of claim 1, wherein identifying at least one subcategory includes accessing a database of subcategory terms for the respective classification. ### Claim 6 (depends on 1) The method of claim 1, further including storing the one or more edit operations in a layer of an edit stack, wherein the layer corresponds to the select subcategory. ### Claim 7 (depends on 6) The method of claim 6, further including applying the one or more edit operations from the layer to another object in a second image associated with the select subcategory. ### Claim 8 A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: segmenting a first image into regions depicting objects; identifying two or more different classifications descriptive of respective objects of the objects in the first image; identifying at least one subcategory for a respective classification of the two or more different classifications, wherein the at least one subcategory has a greater level of specificity than a specificity of the respective classification and the at least one subcategory is represented by a respective semantic term; storing locator information for regions of the firstimage corresponding to the respective objects associated with the at least one subcategory; providing to a user device, the respective semantic term of the at least one sub category; receiving a user selection of at least one semantic term indicating a select subcategory of the at least one subcategory; receiving a user request to apply one or more edit operations to at least one instance of an object in the firstimage associated with the select subcategory; and applying the one or more edit operations to the at least one instance of the object in the firstimage associated with the select subcategory by locating the at least one instance of the object with the location information for the at least one instance of the object. ### Claim 9 (depends on 8) The computer-readable medium of claim 8, wherein the operations further comprise identifying a generic classification of a region of the first image. ### Claim 10 (depends on 8) The computer-readable medium of claim 8, wherein the at least one subcategory includes at least one of a gender, an age or an identification name of a person classification. ### Claim 11 (depends on 8) The computer-readable medium of claim 8, wherein the select subcategory includes more than one instance of the object associated with the select subcategory and the user selection includes a select number of the instances of the object associated with the select subcategory. ### Claim 12 (depends on 8) The computer-readable medium of claim 8, wherein identifying at least one subcategory includes accessing a database of subcategory terms for the respective classification. ### Claim 13 (depends on 8) The computer-readable medium of claim 8, wherein the operation further comprise storing the one or more edit operations in a layer of an edit stack, wherein the layer corresponds to the select subcategory. ### Claim 14 (depends on 13) The computer-readable medium of claim 13, wherein the operation further comprise applying the one or more edit operations from the layer to another object in a second image associated with the select subcategory. ### Claim 15 A system comprising: one or more processors; and one or more computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising: segmenting a first image into regions depicting objects; identifying two or more different classifications descriptive of respective objects of the objects in the first image; identifying at least one subcategory for a respective classification of the two or more different classifications, wherein the at least one subcategory has a greater level of specificity than a specificity of the respective classification and the at least one subcategory is represented by a respective semantic term; storing locator information for regions of the first image corresponding to the respective objects associated with the at least one subcategory; providing to a user device, the respective semantic term of the at least one sub category; receiving a user selection of at least one semantic term indicating a select subcategory of the at least one subcategory; receiving a user request to apply one or more edit operations to at least one instance of an object in the first image associated with the select subcategory; and applying the one or more edit operations to the at least one instance of the object in the first image associated with the select subcategory by locating the at least one instance of the object with the location information for the at least one instance of the object. ### Claim 16 (depends on 15) The system of claim 15, wherein the at least one subcategory includes at least one of a gender, an age or an identification name of a person classification. ### Claim 17 (depends on 15) The system of claim 15, wherein at least one of the at least one subcategory includes more than one instance of an object and the user selection includes a select number of the instances of the select subcategory. ### Claim 18 (depends on 15) The system of claim 15, wherein the select subcategory includes more than one instance of the object associated with the select subcategory and the user selection includes a select number of the instances of the object associated with the select subcategory. ### Claim 19 (depends on 15) The system of claim 15, wherein the operations further comprise storing the one or more edit operations in a layer of an edit stack, wherein the layer corresponds to the select subcategory. ### Claim 20 (depends on 19) The system of claim 19, wherein the operations further comprise applying the one or more edit operations from the layer to another object in a second image associated with the select subcategory.