AUTOMATIC IMAGE-BASED RECOMMENDATIONS USING A COLOR PALETTE

• US 20170098314A1
• Filed: 12/19/2016
• Published: 04/06/2017
• Est. Priority Date: 06/26/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Sayre, III, Paul Barnhart, Dorner, Charles Shearer, Ramos, Gonzalo Alberto
• Granted Patent: US 10,186,054 B2
• Time in Patent Office: Days
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 2207/10024 Color image

Abstract

Systems and methods are described that recommend images, items, and/or metadata based at least in part on a reference color palette or reference color name. A color name can be converted into a representation of the color name in a color space. The reference color can be used to identify images that contain the reference color. The identified images and associated metadata can be analyzed, sorted and provided as an ordered list of items. Systems and methods are also described that identify items that contain colors affiliated with the reference color. Systems and methods are also described that validate color identifier information in metadata associated with an image. Systems and methods are also described that identify non-color specific keywords associated with the reference color.

Claims

1. A computer-implemented method for generating a custom color palette, the computer-implemented method comprising:

under control of a hardware computing device configured with specific computer-executable instructions,

deriving a first color from one or more color images, the first color associated with a color name;

obtaining a plurality of affiliated palettes, wherein each affiliated palette of the plurality of affiliated palettes includes the first color;

identifying at least one second color based at least in part on the plurality of affiliated palettes, wherein at least a subset of the plurality of affiliated palettes includes a color corresponding to the at least one second color; and

generating the custom palette to include at least the first color and the second color.

2. The computer-implemented method of claim 1, wherein each affiliated palette of the plurality of affiliated palettes is associated with a respective weight, and wherein identifying the at least one second color further comprises:

identifying the subset of the plurality of affiliated palettes;

determining a cumulative weight for the at least one second color based at least on respective weights associated with each palette of the subset; and

determining that the cumulative weight has a higher rank than another weight.

3. The computer-implemented method of claim 1, wherein obtaining the plurality of affiliated palettes further comprises:

determining that each affiliated palette, of the plurality of affiliated palettes, includes the first color by including a color that is within a threshold distance from the first color in a color space.

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

receiving a reference color name different from the color name; and

determining, from the reference color name, the color name based at least in part on natural language processing.

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

receiving the color name; and

identifying the one or more color images associated with the color name.

6. A non-transitory computer-readable storage medium storing computer-executable instructions that when executed by a processor perform operations comprising:

deriving a first color from one or more color images;

obtaining a plurality of affiliated palettes, wherein each affiliated palette of the plurality of affiliated palettes includes the first color;

identifying at least one second color based at least in part on the plurality of affiliated palettes, wherein at least a subset of the plurality of affiliated palettes includes a color corresponding to the at least one second color; and

generating a custom palette to include at least the first color and the second color.

7. The non-transitory computer-readable storage medium of claim 6, wherein each affiliated palette of the plurality of affiliated palettes is associated with a respective weight, and wherein identifying the at least one second color further comprises:

identifying the subset of the plurality of affiliated palettes;

determining a cumulative weight for the at least one second color based at least on respective weights associated with each palette of the subset; and

determining that the cumulative weight has a higher rank than another weight.

8. The non-transitory computer-readable storage medium of claim 6, wherein obtaining the plurality of affiliated palettes further comprises:

determining that each affiliated palette, of the plurality of affiliated palettes, includes the first color by including a color that is within a threshold distance from the first color in a color space.

9. The non-transitory computer-readable storage medium of claim 6, wherein the operations further comprise:

receiving a reference color name different from the color name; and

determining, from the reference color name, the color name based at least in part on natural language processing.

10. The non-transitory computer-readable storage medium of claim 6, wherein the operations further comprise:

receiving the color name; and

identifying the one or more color images associated with the color name.

11. The non-transitory computer-readable storage medium of claim 10, wherein each image of the one or more color images is associated with metadata, and wherein identifying the one or more color images further comprises:

determining, from a plurality of color images, that respective metadata of the one or more color images corresponds to the color name.

12. The non-transitory computer-readable storage medium of claim 6, wherein the operations further comprise:

identifying first item data associated with the first color;

identifying second item data associated with the second color; and

providing the first item data and the second item data to a computing device.

13. A system comprising:

a data store configured to at least store computer-executable instructions; and

a hardware processor in communication with the data store, the hardware processor configured to execute the computer-executable instructions to at least;

receive a first color;

obtain a plurality of affiliated palettes, wherein each affiliated palette of the plurality of affiliated palettes includes the first color;

identify at least one second color based at least in part on the plurality of affiliated palettes, wherein at least a subset of the plurality of affiliated palettes includes a color corresponding to the at least one second color; and

generate a custom palette to include at least the first color and the second color.

14. The system of claim 13, wherein each affiliated palette of the plurality of affiliated palettes is associated with a respective weight, and wherein identifying the at least one second color further comprises:

identifying the subset of the plurality of affiliated palettes;

determining a cumulative weight for the at least one second color based at least on respective weights associated with each palette of the subset; and

determining that the cumulative weight has a higher rank than another weight.

15. The system of claim 13, wherein obtaining the plurality of affiliated palettes further comprises:

determining that each affiliated palette, of the plurality of affiliated palettes, includes the first color by including a color that is within a threshold distance from the first color in a color space.

16. The system of claim 13, wherein the hardware processor is further configured to execute the computer-executable instructions to at least:

receive a color name; and

determine the first color based at least in part on the color name.

17. The system of claim 16, wherein the hardware processor is further configured to execute the computer-executable instructions to at least:

determine, from the color name, a secondary color name based at least in part on natural language processing, wherein the first color corresponds to the secondary color name.

18. The system of claim 13, wherein the hardware processor is further configured to execute the computer-executable instructions to at least:

identify a first image that includes the first color; and

identify a second image that includes the second color.

19. The system of claim 18, wherein the hardware processor is further configured to execute the computer-executable instructions to at least:

identify first item data associated with the first image;

identify second item data associated with the second image; and

provide the first item data and the second item data to a computing device.

20. The system of claim 18, wherein identifying that the first image includes the first color further comprises:

determining that the first image includes the first color by including a color that is within a threshold distance from the first color in a color space.