Granted Patent B2

US 12,461,962 · App. 17/366,687 · Granted Nov 4, 2025

Inventors: Kelei Xu (Mountain View, CA); Naveen Gavini (San Francisco, CA); Kevin Yushi Jing (San Francisco, CA); Andrew Huan Zhai (San Mateo, CA); Dmitry Olegovich Kislyuk (San Francisco, CA); Adam Jay Barton (Oakland, CA); Marcelo Reis e Silva de Queiroz (Winter Garden, FL)

Assignee: Pinterest, Inc.

G06F16/532G06F3/0488G06F16/54G06F16/5866G06T7/11G06F3/0482G06F3/04845G06F2203/04808G06T2200/24G06V2201/10

Abstract

Claims (87)

1 . A computer-implemented method, comprising:

causing a presentation of an image on a display of a device, wherein the image includes a representation of a plurality of objects;

causing, concurrent with the presentation of the image, a presentation of a dynamic search control in a first position, the dynamic search control overlaid over the image to encompass a first object represented in a first portion of the image, the plurality of objects including the first object;

receiving an indication of a user interaction to adjust at least one of a position, a shape, or a size of the dynamic search control;

in response to the indication of the user interaction, causing the at least one of the position, the shape, or the size of the dynamic search control to be adjusted, the dynamic search control overlaid over the image in a second position that encompasses a second object represented in a second portion of the image, the plurality of objects including the second object, the second object being different from the first object;

identifying the second object represented in the second portion of the image by processing the second portion of the image corresponding to the second position, the processing including segmenting the second portion of the image;

determining, based at least in part on visual similarities between the identified second object and objects represented in a plurality of images, a plurality of additional images from the plurality of images, the plurality of additional images including representations of a second plurality of objects that are visually similar to the second object; and

causing a second presentation, on the display and concurrent with the image, of at least a portion of the plurality of additional images.

2 . The computer-implemented method of claim 1 , further comprising:

obtaining an interaction with the dynamic search control corresponding to a second user-initiated adjustment of at least one of the position, the shape, or the size of the dynamic search control;

causing a second updated presentation of the dynamic search control concurrent with the image, wherein the second updated presentation corresponds to the second user-initiated adjustment of the at least one of the position, the shape, or the size of the dynamic search control;

processing a third portion of the image corresponding to an area encompassed by the dynamic search control corresponding to the second updated presentation of the dynamic search control to identify a third object represented within the third portion of the image, wherein the third object is different from the first object and the second object;

determining a plurality of second additional images, each of the plurality of second additional images including a representation of a respective second additional object that is visually similar to the third object; and

causing presentation, on the display, of at least a portion of the plurality of second additional images.

3 . The computer-implemented method of claim 1 , further comprising:

obtaining a selection of an additional image from the plurality of additional images;

and performing an action in response to the selection of the additional image.

4 . The computer-implemented method of claim 3 , wherein the action includes at least one of:

initiating a purchase of an additional object represented in the additional image;

presenting a detailed view of the additional image;

presenting additional information corresponding to the additional image;

presenting additional information corresponding to the additional object represented in the additional image;

sharing the additional image;

saving the additional image; or presenting a video corresponding to the additional object represented in the additional image.

5 . The computer-implemented method of claim 1 , further comprising:

identifying a plurality of keywords associated with the plurality of additional images; and

causing presentation, on the display, of at least one of the plurality of keywords.

6 . A computing system, comprising:

one or more processors; and

a memory coupled to the one or more processors and storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least:

cause a presentation of an image on a display, wherein the image includes a representation of a plurality of objects;

cause a user-adjustable dynamic search control to be presented on the display in a first position, the user-adjustable dynamic search control being overlaid over a first portion of the image to encompass a first object represented in the first portion of the image;

receive an indication of a user interaction with the user-adjustable dynamic search control to adjust at least one of a position, a shape, or a size of the user-adjustable dynamic search control;

in response to the indication of the user interaction, causing at least one of the position, the shape, or the size of the user-adjustable dynamic search control to be adjusted relative to the image, the user-adjustable dynamic search control being overlaid over a second portion of the image to encompass a second object, the second object being different from the first object; and

identify the second object represented in the second portion of the image by processing at least a portion of the second portion of the image, the processing including segmenting the second portion of image;

determine, based at least in part on visual similarities between the identified second object and objects represented in a plurality of images, a plurality of additional images from the plurality of images, the plurality of additional images including representations of a second plurality of objects that are visually similar to the second object; and

cause a second presentation on the display of at least a portion of the plurality of additional images.

7 . The computing system of claim 6 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

obtain a second user interaction with the user-adjustable dynamic search control;

in response to the second user interaction, process a third portion of the image encompassed by the user-adjustable dynamic search control to identify a third object represented within the third portion of the image;

determine a plurality of second additional images, each of the plurality of second additional images including representations of a third plurality of objects that are visually similar to the third object; and

cause at least a portion of the plurality of second additional images to be presented on the display.

8 . The computing system of claim 7 , wherein the second user interaction corresponds to an adjustment of at least one of a position, a size, or a shape of the user-adjustable dynamic search control, such that the third portion of the image encompassed by the user-adjustable dynamic search control encompasses the third object.

9 . The computing system of claim 6 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

identify a plurality of keywords associated with the plurality of additional images;

and cause at least one of the plurality of keywords to be presented on the display.

10 . The computing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

obtain a selection of one or more keyword of the plurality of keywords;

determine, based at least in part on the selected one or more keywords, a ranking of the plurality of additional images; and

cause the plurality of additional images to be presented on the display in accordance with the ranking.

11 . The computing system of claim 9 , wherein identifying the plurality of keywords is based at least in part on a frequency that the plurality of keywords is associated with the plurality of additional images.

12 . The computing system of claim 9 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

cause a known object identifier to be presented on the display, the known object identifier being associated with a second object represented in the image and indicating an availability of a plurality of second additional images, each of the plurality of second additional images including representations of a third plurality of objects that are visually similar to the second object.

13 . The computing system of claim 6 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

obtain a first selection of an additional image from the plurality of additional images;

cause an action control indication to be presented on the display concurrent with a presentation of the additional image;

obtain a second selection of the action control indication; and

initiate an action associated with the action control indication.

14 . The computing system of claim 6 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to at least:

generate a ranking of the plurality of additional images,

wherein the presentation of at least the portion of the plurality of additional images corresponds to the ranking of the plurality of additional images.

15 . The computing system of claim 6 , wherein processing at least the portion of the image to identify the object of interest includes generating an image segment of the object of interest.

16 . A computer-implemented method, comprising:

causing an image to be presented on a display, wherein the image includes a representation of a plurality of objects;

causing a dynamic search control to be presented on the display in a first position to encompass a first portion of the image, the dynamic search control being overlaid over the presentation of the image on the display, such that the dynamic search control encompass a first object represented in the first portion of the image of the plurality of objects;

obtaining an indication of a user interaction with the dynamic search control to adjust corresponding to an adjustment of at least one of a position, a shape, or a size of the dynamic search control;

causing, in response to the indication of the user interaction, the at least one of the position, the shape, or the size of the dynamic search control to be adjusted in accordance with the user interaction, an updated presentation of the dynamic search control overlaid over the image, such that the dynamic search control being overlaid over the image in a second position to encompass a second object represented in a second portion of the image encompasses a second object of the plurality of objects that is represented in a first portion of the image, wherein the updated presentation corresponds to the adjustment of the at least one of the position, the shape, or the size of the dynamic search control;

identifying, based at least in part on a segmentation of the second portion of the image, the second object represented in the second portion of the image;

determining, based at least in part on a visual similarity between the identified second object and a third object represented in a first additional image, the first additional image from a first plurality of additional images, each the third object represented in the first additional image being visually similar to the second object; and

causing the first additional image to be presented on the display.

17 . The computer-implemented method of claim 16 , further comprising:

obtaining a second interaction with the dynamic search control corresponding to a second adjustment of at least one of the position, the size, or the shape of the dynamic search control, such that the dynamic search control is overlaid over the image so that it encompasses a second portion of the image;

determining a third object of the plurality of objects represented in the second portion of the image;

determining a plurality of second additional images, each of the plurality of second additional images including a representation of a respective second additional object that is visually similar to the third object; and

causing presentation on the display of at least a portion of at least one of the plurality of second additional images.

18 . The computer-implemented method of claim 16 , further comprising:

identifying a plurality of keywords associated with the plurality of additional images;

causing the plurality of keywords to be presented on the display;

obtaining a first selection of a first keyword from the plurality of keywords;

determining a ranking of the plurality of additional images based at least in part on the first selection of the first keyword;

obtaining a second selection of a second keyword from the plurality of keywords; and

determining an updated ranking of the plurality of additional images based at least in part on the second selection of the second keyword,

wherein the presentation of at least the portion of at least one of the plurality of additional images on the display is based at least in part on the updated ranking.

19 . The computer-implemented method of claim 16 , further comprising:

determining a known object represented in the image; and

causing a known object identifier to be presented in association with the known object, wherein the known object identifier indicates an availability of a plurality of second additional images, each of the plurality of second additional images including a representation of a respective second additional object that is visually similar to the known object.

20 . The computer-implemented method of claim 16 , wherein determining the second object represented in the first portion of the image includes generating an image segment of the second object.

Assignments (2)

Continuity (3)

References Cited (123)