Systems and methods for color palette suggestions

• US 9,910,897 B2
• Filed: 05/01/2015
• Issued: 03/06/2018
• Est. Priority Date: 05/06/2014
• Status: Active Grant

• Current Assignee: Shutterstock Incorporated
• Original Assignee: Shutterstock Incorporated
• Inventors: Becker, Chris, Kroner, David, Blaurock, Steve
• Primary Examiner(s): Syed, Farhan
• Application Number:
  US14/701,549
• Publication Number:
  US 20150324392A1
• Time in Patent Office: 1,040 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• 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

Abstract

A method and system for conducting image search comprising: searching a first database to locate a set of pertinent images, iteratively performing the following operations for each image in the set of pertinent images: (a) extracting the histogram of red green and blue colors (RGB colors) from a given image; (b) distilling the extracted RGB colors down to create a reduced color palette for the given image; (c) segmenting the extracted RGB colors into a set of segments representing distinct parts of the color spectrum; (d) selecting a subset of segments to assemble a color palette for the given image; and (e) updating the assembled color palette and the customer behavior score for the given image in the first database; and generating a display of suggested color palettes for the search query.

Claims

1. A method for providing a display of color palettes in response to a user search query, the method comprising:

receiving from a user a search query on a user interface of a computing device;

searching a database to locate images responsive to the search query, wherein for each image, the database comprises an image representation, a set of keywords associated with the image, a customer behavior score for each keyword in the set of keywords indicating user interest in the image, and a list of keywords previously used to locate the image;

extracting red, green, and blue (RGB) colors for each responsive image to provide extracted RGB colors from the responsive image;

creating a reduced color palette comprising a plurality of colors for each responsive image based on a proximity of the extracted RGB colors in a RGB color space;

assigning, to each of the plurality of colors for a responsive image, a color volume score and a color weight score, wherein the color volume score indicates a percentage of the responsive image covered by the respective color, and the color weight score indicates the percentage of the respective color in the responsive image;

ascertaining a percentage of a set of proximate colors in the responsive image, wherein each color in the set of proximate colors is located within a predefined distance from the respective color in the RGB color space;

identifying a measure of the distance between the respective color and the set of proximate colors in the RGB color space;

indexing the color volume score, the color weight score, and the percentage of the set of proximate colors for the respective color in a search engine for a subsequent image search;

dividing the extracted RGB colors for each responsive image into a set of segments representing visually distinct parts of a color spectrum, and black and white colors;

selecting a subset of segments, from the set of segments, satisfying a predetermined criterion to assemble a color palette for each responsive image;

updating the color palette and the customer behavior score for each responsive image in the database; and

providing for display of suggested color palettes for the search query based on the updated color palettes for the responsive images.

2. The method of claim 1, further comprising:

assigning, for each segment in the set of segments, a color score to each color in a respective segment to ascertain a color that represents the respective segment; and

assigning a segment score to the respective segment by aggregating the color volume scores of each color in the respective segment.

3. The method of claim 1, further comprising:

assigning a color score to each color in a respective segment to ascertain a color that represents the respective segment; and

assigning a segment score for each segment in the set of segments, wherein the segment score for a respective segment is computed by aggregating color volume scores of each color in the respective segment.

4. The method of claim 3, further comprising designating at least one segment in the set of segments having the highest color score to represent the responsive image.

5. The method of claim 1, wherein the color weight score for a respective color is weighted based on the percentage for every color other than the respective color in the responsive image and the color distance in the RGB color space between the respective color and every color other than the respective color in the responsive image.

6. The method of claim 2,

wherein the segment score is determined by a product of the color volume score, a color lightness measure, and a color chroma measure, and

wherein the color having the highest segment score in a respective segment is designated to represent the respective segment.

7. The method of claim 1, further comprising selecting a predefined number of segments having the highest segment scores for assembling a color palette representation for a responsive image.

8. The method of claim 1, wherein the customer behavior score is based on previous searches indicating the user interest in the responsive image.

9. The method of claim 8, wherein the user interest is indicated by at least one of the following:

the user purchasing the responsive image, the user hovering a cursor over a thumbnail version of the responsive image to view an enlarged version of the responsive image, and the user adding the responsive image to a favorites list.

10. The method of claim 1, further comprising:

aggregating customer behavior scores associated with each search query; and

identifying most relevant keywords or categories for a responsive image using the aggregated customer behavior scores.

11. The method of claim 1, further comprising:

aggregating customer behavior scores associated with each search query over a period of time; and

representing a customer activity for a specific period of interest using the aggregated customer behavior scores.

12. A system for providing a display of color palettes in response to a user search query, the system comprising:

a processor configured to execute operations to;

receive from a user a search query on a user interface of a computing device;

search a database to locate images responsive to the search query, wherein for each image, the database comprises an image representation, a set of keywords associated with the image, a customer behavior score for each keyword in the set of keywords indicating user interest in the image, and a list of keywords previously used to locate the image;

extract red, green, and blue (RGB) colors for each responsive image to provide extracted RGB colors from the responsive image;

create a reduced color palette comprising a plurality of colors for each responsive image based on a proximity of the extracted RGB colors in a RGB color space;

assign, to each of the plurality of colors for a responsive image, a color volume score and a color weight score, wherein the color volume score indicates a percentage of the responsive image covered by the respective color, and the color weight score indicates the percentage of the respective color in the responsive image;

ascertain a percentage of a set of proximate colors in the responsive image, wherein each color in the set of proximate colors is located within a predefined distance from the respective color in the RGB color space;

identify a measure of the distance between the respective color and the set of proximate colors in the RGB color space;

index the color volume score, the color weight score, and the percentage of the set of proximate colors for the respective color in a search engine for a subsequent image search;

divide the extracted RGB colors for each responsive image into a set of segments representing visually distinct parts of a color spectrum, and black and white colors;

select a subset of segments from the set of segments satisfying a predetermined criterion to assemble a color palette for each responsive image;

update the color palette and the customer behavior score for each responsive image in the database; and

provide for display of suggested color palettes for the search query based on the updated color palettes for the responsive images.

13. The system of claim 12, the processor further configured:

assign a color score to each color in a respective segment to ascertain a color that represents the respective segment; and

assign a segment score to the respective segment by aggregating color volume scores of each color in the respective segment.

14. The system of claim 13, the processor further configured to designate at least one segment in the set of segments having the highest color score to represent the responsive image.

15. The system of claim 12, wherein the color weight score for a respective color is weighted based on at least one of:

the percentage for every color other than the given color in the responsive image, or color distance in the RGB color space between the respective color and every color other than the respective color in the responsive image.

16. The system of claim 13,

wherein the segment score is determined by a product of the color volume score, a color lightness measure, and a color chroma measure, and

wherein the color having the highest segment score in a respective segment is designated to represent the respective segment.

17. The system of claim 12, wherein the customer behavior score is based on previous searches indicating the user interest in the responsive image and the user interest is indicated by at least one of the following:

the user purchasing the responsive image, the user hovering a cursor over a thumbnail version of the responsive image to view an enlarged version of the responsive image, and the user adding the responsive image to a favorites list.

18. The system of claim 12, the processor further configured to:

aggregate customer behavior scores associated with each search query; and

to identify most relevant keywords or categories for a responsive image using the aggregated customer behavior scores.

19. The system of claim 12, the processor further configured to:

aggregate customer behavior scores associated with each search query over a period of time; and

represent a customer activity for a specific period of interest using the aggregated customer behavior scores.

20. A non-transitory machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method for providing a display of color palettes in response to a user search query, the method comprising

receiving from a user a search query on a user interface of a computing device;

searching a database to locate images responsive to the search query, wherein for each image, the database comprises an image representation, a set of keywords associated with the image, a customer behavior score for each keyword in the set of keywords indicating user interest in the image, and a list of keywords previously used to locate the image;

extracting red, green, and blue (RGB) colors for each responsive image to provide extracted RGB colors from the responsive image;

creating a reduced color palette comprising a plurality of colors for each responsive image based on a proximity of the extracted RGB colors in a RGB color space;

assigning, to each of the plurality of colors for a responsive image, a color volume score and a color weight score, wherein the color volume score indicates a percentage of the responsive image covered by the respective color, and the color weight score indicates the percentage of the respective color in the responsive image;

ascertaining a percentage of a set of proximate colors in the responsive image, wherein each color in the set of proximate colors is located within a predefined distance from the respective color in the RGB color space;

identifying a measure of the distance between the respective color and the set of proximate colors in the RGB color space;

indexing the color volume score, the color weight score, and the percentage of the set of proximate colors for the respective color in a search engine for a subsequent image search;

dividing the extracted RGB colors for each responsive image into a set of segments representing visually distinct parts of a color spectrum, and black and white colors;

selecting a subset of segments, from the set of segments, satisfying a predetermined criterion to assemble a color palette for each responsive image;

updating the color palette and the customer behavior score for each responsive image in the database; and

providing for display of suggested color palettes for the search query based on the updated color palettes for the responsive images.