Fashion preference analysis

Patent metadata

Field	Value
Publication number	US-10013710-B2
Application number	US-201414326125-A
Country	US
Kind code	B2
Filing date	Jul 8, 2014
Priority date	Apr 17, 2014
Publication date	Jul 3, 2018
Grant date	Jul 3, 2018

Abstract

A machine may be configured to determine fashion preferences of users and to provide item recommendations to the users based on the users' fashion preferences. For example, the machine receives an image of a user and a set of spatial data indicating a position of the body of the user in a three-dimensional space. The machine may perform an analysis of the image and the set of spatial data. The performing of the analysis may include extracting, from the image, an image swatch that depicts a portion of an item worn by the user. The machine may identify a fashion preference of the user based on the analysis of the image and of the set of spatial data. The machine may identify an item that corresponds to the fashion preference of the user within an inventory of fashion items and may generate a recommendation of the identified fashion item.

First claim

What is claimed is:

1. A system comprising:
one or more hardware processors; and
a non-transitory machine-readable medium for storing instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
receiving an image of a user and a set of spatial data indicating a position of the body of the user in a three-dimensional space, the received image and the received set of spatial data captured at a point in time;
identifying a location in the received image, corresponding to a particular body part of the user, based on one or more identifiers of bone joints of the user in a skeleton array generated based on the set of spatial data indicating a position of the body of the user in the three-dimensional space;
performing an analysis of the received image and of the received set of spatial data, the performing of the analysis including extracting an image swatch from the received image, the image swatch depicting a portion of an item worn by the user at the point in time, the image swatch being extracted from the identified location in the received image, the image swatch depicting the portion of the item worn by the user on the particular body part; and
identifying a fashion preference of the user based on the analysis of the received image and of the received set of spatial data.

2. The system of claim 1 , wherein the operations further comprise:
generating, based on the received image and the received set of spatial data, a model that represents the body of the user at the point in time.

3. The system of claim 2 , wherein the performing of the analysis of the received image and of the received set of spatial data includes:
analyzing a pose of the user depicted in the model that represents the body of the user at the point in time;
identifying, based on the analysis of the pose, an area of the model that represents the particular body part of the user that is unobstructed by an object; and
clustering the model with one or more other models representing the body of the user at other times, based on the area of the model that represents the particular body part of the user and the same area of one or more other models being unobstructed by an object, the one or more other models representing the body of the user.

4. The system of claim 2 , wherein the model includes the one or more identifiers of the bone joints of the user.

5. The system of claim 4 , wherein the operations further comprise:
performing an analysis of the image swatch; and
determining, based on the analysis of the image swatch, one or more attribute-value pairs that characterize the item worn by the user on the particular body part.

6. The system of claim 5 , wherein the performing of the analysis of the image swatch includes:
extracting one or more visual features from the image swatch, and
wherein the determining of one or more attribute-value pairs is based on the one or more visual features extracted from the image swatch.

7. The system of claim 5 , wherein the operations further comprise:
accessing a plurality of attribute-value pairs that characterize one or more items worn by the user during a period of time, the one or more items including the item;
accessing a plurality of received images received during the period of time;
determining a frequency of the user wearing items characterized by a particular attribute-value pair of the plurality of attribute-value pairs during the period of time, and
wherein the identifying of the fashion preference of the user is based on the frequency of the user wearing items characterized by the particular attribute-value pair of the plurality of attribute-value pairs during the period of time.

8. The system of claim 1 , wherein the operations further comprise:
identifying an item that corresponds to the fashion preference of the user within an inventory of fashion items based on a search of the inventory of fashion items.

9. The system of claim 8 , wherein the identifying of the item that corresponds to the fashion preference of the user includes:
performing of a search of the inventory of fashion items based on the image swatch, the performing of the search including comparing, according to a particular search rule, the image swatch and one or more images depicting fashion items within the inventory.

10. The system of claim 8 , wherein the identifying of the item that corresponds to the fashion preference of the user includes:
performing of a search of the inventory of fashion items based on one or more attribute-value pairs that characterize the item worn by the user on a particular body part of the user, the one or more attribute-value pairs being determined based on one or more visual features extracted from the image swatch.

11. The system of claim 8 , wherein the identifying of the item that corresponds to the fashion preference of the user includes:
performing a similarity search of the fashion inventory.

12. The system of claim 8 , wherein the identifying of the item that corresponds to the fashion preference of the user includes:
performing a co-ordination search of the fashion inventory based on one or more visual features extracted from the image swatch.

13. The system of claim 8 , wherein the operations further comprise:
generating a recommendation of the fashion item identified during the search of the fashion inventory.

14. A method comprising:
receiving an image of a user and a set of spatial data indicating a position of the body of the user in a three-dimensional space, the received image and the received set of spatial data captured at a point in time;
identifying a location in the received image, corresponding to a particular body part of the user, based on one or more identifiers of bone joints of the user in a skeleton array generated based on the set of spatial data indicating a position of the body of the user in the three-dimensional space;
performing, by one or more hardware processors, an analysis of the received image and of the received set of spatial data, the performing of the analysis including extracting an image swatch from the received image, the image swatch depicting a portion of an item worn by the user at the point in time, the image swatch being extracted from the identified location in the received image, the image swatch depicting the portion of the item worn by the user on the particular body part; and
identifying a fashion preference of the user based on the analysis of the received image and of the received set of spatial data.

15. The method of claim 14 , further comprising:
generating, based on the received image and the received set of spatial data, a model that represents the body of the user at the point in time.

16. The method of claim 15 , wherein the performing of the analysis of the received image and of the received set of spatial data includes:
analyzing a pose of the user depicted in the model that represents the body of the user at the point in time;
identifying, based on the analysis of the pose, an area of the model that represents the particular body part of the user that is unobstructed by an object; and
clustering the model with one or more other models representing the body of the user at other times, based on the area of the model that represents the particular body part of the user and the same area of one or more other models being unobstructed by an object, the one or more other models representing the body of the user.

17. The method of claim 15 , wherein the model includes the

Assignees

• Di Wei
• Jagadeesh Vignesh
• Piramuthu Robinson
• Churchill Elizabeth
• Bhardwaj Anurag
• Ebay Inc

Inventors

• Di Wei
• Jagadeesh Vignesh
• Piramuthu Robinson
• Churchill Elizabeth
• Bhardwaj Anurag

Classifications

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06K9/00362

  Physics · mapped topic

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06V40/20

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06V20/64

  Three-dimensional [3D] objects · CPC title