SYSTEMS AND METHODS FOR COLOR PALLETE SUGGESTION

• US 20150324394A1
• Filed: 05/01/2015
• Published: 11/12/2015
• Est. Priority Date: 05/06/2014
• Status: Active Grant

• Current Assignee: Shutterstock Incorporated
• Original Assignee: Shutterstock Incorporated
• Inventors: Becker, Chris, Kroner, David, Blaurock, Steve
• Granted Patent: US 10,489,408 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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

Methods and systems for searching images in response to a keyword and color palette selection criteria. The method comprising: searching a first database to locate a set of pertinent images satisfying a keyword and color palette selection criteria; displaying the set of pertinent images and the set of colors; generating a set of suggested color palettes; displaying on the user interface the set of pertinent images which match the keyword and the single color specified by the single color option; displaying the set of pertinent images which match the combination specified by the first set of colors; dynamically extracting and displaying the color palette from a first image in response to receiving an input indicating a cursor hovering over the first image; and performing a first set of operations in response to receiving a user selected color palette extracted from the first image.

Claims

1. A method for searching images in response to a user presenting a keyword and a color palette selection criteria on a user interface of a computing device, the method comprising:

searching a first database to locate a set of pertinent images satisfying the keyword and the color palette selection criteria, the first database comprising at least one image, a set of keywords associated with each of the images, a customer behavior score for each keyword in the set of keywords, and a set of colors associated with each of the images;

displaying the set of pertinent images and the set of colors associated with the set of pertinent images on the user interface;

generating a set of suggested color palettes by iteratively extracting a suggested color palette from each image in the set of pertinent images;

displaying on the user interface, in response to receiving a user selection of a single color option, the set of pertinent images which match the keyword and the single color specified by the single color option;

displaying on the user interface, in response to receiving an input of a first set of colors selected via a color palette suggestion option, the set of pertinent images which match the combination specified by the first set of colors;

dynamically extracting and displaying on the user interface the color palette from a first image in the set of pertinent images in response to receiving an input indicating a cursor hovering over the first image on the user interface; and

performing a first set of operations in response to receiving a user selected color palette extracted from the first image.

2. The method of claim 1, further comprising the steps of generating a visually distinct set of suggested color palettes by filtering visually similar color palettes from the set of suggested color palettes by performing the following steps for each palette in the set of suggested color palettes:

creating an index of all combinations of N−

1 colors,

count the number of times each set of N−

1 colors is present in the index,

comparing the N^th colors for each color palette from the set of suggested color palettes if there is more than one instance of a set of N−

1 colors, and

removing one of the color palettes from the result set if the distance between any two N^th colors is below a predefined threshold.

3. The method of claim 2, further comprising the steps of performing the following operations if a single color is selected via a single color selection option:

retrieving the set of pertinent images from the first database satisfying the keyword criterion,

comparing the single color to the combination of the color weight and the color volume score in each image that contains the selected color, and

displaying the result set comprising the images that match the keyword criterion and the single color on the user interface.

4. The method of claim 2, further comprising the steps of displaying N+1 color palettes when a multicolor palette with N colors is selected via the color palette suggestion option.

5. The method of claim 4, wherein the list of colors is sorted by the number of images in the set of pertinent images displaying a particular color in the list of colors.

6. The method of claim 1, further comprising the step of accepting a selected color weight score criteria by manually defining the proportion of each color via a control located on a first interface.

7. The method of claim 1, further comprising the step of selecting the color weight score criteria by manually selecting an image from the user interface.

8. The method of claim 7, further comprising the step of extracting a color histogram of the manually selected image and searching the second database to locate the set of pertinent images having matching proportions of each color displayed in the color histogram, wherein the second database comprises a color, a color volume score and an image, wherein the color volume score for the color indicates the percentage of the image covered by the color.

9. The method of claim 1, wherein for a given three color palette, visually similar color palettes share two of the same colors and the third color is a near match.

10. The method of claim 1, wherein the first set of operations comprise:

retrieving the top four colors from the first image and the retrieving the color volume scores for the top four colors in the first image,

searching the second database to locate the set of pertinent images satisfying the keyword and a threshold color volume score criteria, and

generating for each color, a ranked display of the set of pertinent images based on the color volume scores of each image in the set of pertinent images.

11. The method of claim 10, further comprising the step of searching the second database in response to receiving a user selected keyword, a first color criteria and a color weight score criteria to locate the set of pertinent images satisfying the keyword, the first color criteria and the color weight score criteria.

12. The method of claim 11, further comprise searching the second database in response to receiving a user selected keyword, a first color criteria, a color volume score and a color weight score criteria to locate the set of pertinent images satisfying the keyword, the first color criteria, the color volume score and the color weight score criteria.

13. A system for searching images in response to receiving, on a user interface of a computing device, a user presented keyword and a color palette selection criteria, the system comprising:

at least one processor and at least one non-volatile computer-readable storage medium encoded with executable instructions that, when executed by the at least one processor, causes the at least one processor to provide a display of searched images, the system comprising;

a database search unit configured to search a first database to locate a set of pertinent images satisfying the keyword and the color palette selection criteria, the first database comprising an image representation (image), a set of keywords associated with the image, a customer behavior score for each keyword in the set of keywords, and a set of colors associated with the image;

an image display unit configured to display the set of pertinent images and the set of colors associated with the set of pertinent images on the user interface;

a color palette generation unit configured to generate a set of suggested color palettes by iteratively extracting a suggested color palette from each image in the set of pertinent images;

a single color image search unit configured to display on the user interface, in response to the receiving a single color option and a single color selection, the set of pertinent images which match the keyword and the single color selection;

a color palette suggestion unit configured to display on the user interface, in response to receiving a first set of colors by receiving a color palette suggestion option, the set of pertinent images which match the combination specified by the first set of colors;

a user interest management unit configured to dynamically extract and display on the user interface the color palette from a first image in response receiving input of the user hovering over the first image on the user interface; and

a first image processing unit configured to perform a first set of operations in response to receiving a user selected color palette, wherein the color palette is extracted from the first image.

14. The system of claim 13, wherein the color palette suggestion unit is further configured to generate a visually distinct set of suggested color palettes by filtering visually similar color palettes from the set of suggested color palettes by performing the following operations for each palette in the set of suggested color palettes:

create an index of all combinations of N−

1 colors,

count the number of times each set of N−

1 colors is present in the index,

compare the N^th colors for each color palette from the set of suggested color palettes if there is more than one instance of a set of N−

1 colors, and

remove one of the color palettes from the result set if the distance between any two N^th colors is below a predefined threshold.

15. The system of claim 14, further configured to perform the following operations if a single color is selected via a single color selection option:

retrieve the set of pertinent images from the first database that match the keyword,

compare the single color to the combination of the color weight and the color volume score in each image that contains the selected color, and

display the result set comprising the images that match the keyword and the single color on the user interface.

16. The system of claim 14, further configured to display N+1 color palettes when a multicolor palette with N colors is selected via the color palette suggestion option.

17. The system of claim 16, wherein the list of colors is sorted by the number of images in the set of pertinent images displaying a particular color in the list of colors.

18. The system of claim 13, further configured to present a color weight score selection option on the user interface, whereby the proportion of each color is manually defined via a control located on a first interface.

19. The system of claim 13, further configured to receive a color weight score criteria indicated by a manually selected image from the user interface.

20. The system of claim 19, further configured to extract a color histogram of the manually selected image and searching the second database to locate the set of pertinent images having matching proportions of each color displayed in the color histogram, wherein the second database comprises a color, a color volume score and an image, wherein the color volume score for the color indicates the percentage of the image covered by the color.

21. The system of claim 13, wherein for a given three color palette, visually similar color palettes share two of the same colors and the third color is a near match.

22. The system of claim 13, wherein the first set of operations comprise:

retrieving the top four colors from the first image and retrieving the color volume scores for the top four colors in the first image,

searching the second database to locate the set of pertinent images satisfying the keyword and a threshold color volume score criteria, and

generating for each color in the selected image a ranked display of the set of pertinent images, wherein the ranking of the images is based on how close in volume the colors of a given image matches the volume of the color for which the ranked display is being generated.

23. The system of claim 22, further configured to search the second database in response to receiving the keyword, a first color criteria and a color weight score criteria to locate the set of pertinent images satisfying the keyword, the first color criteria and the color weight score criteria.

24. The system of claim 23, further configured to search the second database in response to receiving the keyword, a first color criteria, a color volume score and a color weight score criteria to locate the set of pertinent images satisfying the keyword, the first color criteria, the color volume score and the color weight score criteria.