Re-Ranking item recommendations based on image feature data

• US 9,213,991 B2
• Filed: 03/18/2014
• Issued: 12/15/2015
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Bhardwaj, Anurag, Piramuthu, Robinson, Sundaresan, Neelakantan
• Primary Examiner(s): Dang, Duy M
• Application Number:
  US14/218,704
• Publication Number:
  US 20140201027A1
• Time in Patent Office: 637 Days
• Field of Search: 382/165, 705/26.7
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

An apparatus and method to adjust item recommendations are disclosed herein. A first image attribute of a query image is compared to a second image attribute of each of a plurality of inventory images of a plurality of inventory items to identify the inventory items similar to the query image. Item recommendations comprising the identified inventory items in a first listing order are provided for display at a remote device. A second listing order of the identified inventory items is determined based on a user preference for a particular one of the identified inventory items. At least the second listing order is provided to the remote device for re-display of the item recommendations in accordance with the second listing order.

Claims

1. A method comprising:

identifying items each respectively depicted in an item image among a set of item images, the identifying of the items being performed by a processor of a machine based on a comparison of an image attribute of a query image to an image attribute of each item image among the set of item images;

presenting recommendations of the identified items according to a rank order based on degrees of similarity between the query image and each item image among the set of item images; and

re-ranking the recommendations in response to a detected selection of a recommendation from among the recommendations presented according to the rank order.

2. The method of claim 1 further comprising:

receiving the query image within a query submitted from a remote device.

3. The method of claim 1 further comprising:

receiving a photograph as the query image from a remote device.

4. The method of claim 3, wherein:

the received photograph depicts at least one of a color, a pattern, a textile, an article of clothing, or a portion of the article of clothing.

5. The method of claim 1 further comprising:

detecting the selection of the recommendation from among the recommendations presented according to the rank order.

6. The method of claim 5, wherein:

the detecting of the selection includes detecting a user preference for the recommendation among the presented recommendations.

7. The method of claim 1, wherein:

the re-ranking of the recommendations includes identifying a color shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

8. The method of claim 1, wherein:

the re-ranking of the recommendations includes identifying a pattern shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

9. The method of claim 1, wherein:

the re-ranking of the recommendations includes elevating a rank of a test recommendation among the recommendations based on its corresponding item image being less similar to the query image than at least one further recommendation among the recommendations.

10. A system comprising:

one or more processors;

a comparison module that configures at least one processor among the one or more processors to;

identify items each respectively depicted in an item image among a set of item images, the identifying of the items being based on a comparison of an image attribute of a query image to an image attribute of each item image among the set of item images; and

present recommendations of the identified items according to a rank order based on degrees of similarity between the query image and each item image among the set of item images; and

a re-rank module that configures at least one processor among the one or more processors to re-rank the recommendations in response to a detected selection of a recommendation from among the recommendations presented according to the rank order.

11. The system of claim 10 further comprising:

a user interest module that configures at least one processor among the one or more processors to detect the selection of the recommendation from among the recommendations presented according to the rank order.

12. The system of claim 11, wherein:

the user interest module configures at least one processor among the one or more processors to detect a user preference for the recommendation among the presented recommendations.

13. The system of claim 10, wherein:

the re-rank module configures at least one processor among the one or more processors to identify a color shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

14. The system of claim 10, wherein:

the re-rank module configures at least one processor among the one or more processors to identify a pattern shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

15. The system of claim 10, wherein:

the re-rank module configures at least one processor among the one or more processors to elevate a rank of a test recommendation among the recommendations based on its corresponding item image being less similar to the query image than at least one further recommendation among the recommendations.

16. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

identifying items each respectively depicted in an item image among a set of item images, the identifying of the items being based on a comparison of an image attribute of a query image to an image attribute of each item image among the set of item images;

presenting recommendations of the identified items according to a rank order based on degrees of similarity between the query image and each item image among the set of item images; and

re-ranking the recommendations in response to a detected selection of a recommendation from among the recommendations presented according to the rank order.

17. The non-transitory machine-readable storage medium of claim 16, wherein the operations further comprise:

receiving a photograph as the query image from a remote device, the received photograph depicting at least one of a color, a pattern, a textile, an article of clothing, or a portion of the article of clothing.

18. The non-transitory machine-readable storage medium of claim 16, wherein:

the re-ranking of the recommendations includes identifying a color shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

19. The non-transitory machine-readable storage medium of claim 16, wherein:

the re-ranking of the recommendations includes identifying a pattern shared in common between the query image and the selected recommendation among the recommendations presented according to the rank order.

20. The non-transitory machine-readable storage medium of claim 16, wherein:

the re-ranking of the recommendations includes elevating a rank of a test recommendation among the recommendations based on its corresponding item image being less similar to the query image than at least one further recommendation among the recommendations.