Generating color similarity measures

• US 10,084,941 B2
• Filed: 04/30/2014
• Issued: 09/25/2018
• Est. Priority Date: 04/30/2014
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Moroney, Nathan, Gottwals, Melanie M, Tastl, Ingeborg
• Primary Examiner(s): Nguyen, Madelein T
• Application Number:
  US15/307,349
• Publication Number:
  US 20170048419A1
• Time in Patent Office: 1,609 Days
• Field of Search: None
• CPC Class Codes: G06F 18/24147 Distances to closest patterns, e.g. nearest neighbour classification
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: H04N 1/60 Colour correction or control H04N1/54 takes precedence
• CPC Class Codes: H04N 1/6008 with primary colour signals, e.g. RGB or CMY(K)

Abstract

A system including a memory to store instructions and initial color representations and a processor to execute the instructions in the memory to reference a database having a set of lexical color classifiers, transform each of at least a pair of initial color representations to color values associated with the set of lexical color classifiers, and generate a relative similarity measure related to the at least a pair of initial color representations based on the color values associated with the set of lexical color classifiers.

Claims

1. A system comprising:

a memory to store instructions and initial color representations; and

a processor to execute the instructions in the memory to;

reference a database having a set of lexical color classifiers;

transform each of at least a pair of initial color representations to color values associated with the set of lexical color classifiers; and

generate a color similarity measurement related to the at least a pair of initial color representations based on the color values associated with the set of lexical color classifiers,

wherein each of the initial color representations has an initial color attribute value that is transformed into lexical color attribute values for each of the lexical color classifiers and

wherein the initial color attribute values have n number of color dimensions and the set of lexical color classifiers have m number of color dimensions, wherein n is less than m.

2. The system of claim 1, comprising the processor to execute the instructions in the memory to:

select the database from a larger database based on the initial color representations.

3. The stem of claim 1, wherein generating the color similarity measurement comprises generating a cosine similarity measurement.

4. The system of claim 1, further comprising a print to print based on the color similarity measurement.

5. The system of claim 1, further comprising instructions in the memory executable by the processor to determining if the color similarity measurement indicates a match.

6. A method of measuring color similarity comprising:

receiving an initial color representation for each of at least a pair of image elements;

selecting a set of lexical color classifiers;

transforming each of the initial color representations to the set of lexical color classifiers,

wherein each of the initial color representations has an associated numeric initial color attribute value transformed into a color value for each of the set of lexical color classifiers

and wherein the initial color attribute values have n number of color dimensions and the set of lexical color classifiers have m number of color dimensions, wherein n is less than m;

comparing the initial color representations of the at least pair of color images based on the set of lexical color classifiers; and

generating a relative similarity measurement of the compared initial color representations.

7. The method of claim 6, comprising:

transforming the initial color representations into a positive numeric value in more than one of the set of lexical color classifiers.

8. The method of claim 6, wherein each of the set of lexical color representations Is a text string.

9. The method of claim 6, comprising:

indicating a color match of the initial color representations for the relative similarity having at least a predetermined value.

10. The method of claim 6, wherein the selecting of the set of lexical color classifiers comprises:

a process of machine color naming.

11. The method of claim 6, comprising:

reproducing colors achieving a predetermined relative similarity.

12. The method of claim 6, wherein generating the relative similarity measurement is performed using cosine similarity.

13. The method of claim 6, wherein the transforming comprises:

a k-nearest neighbor association.

14. The method of claim 6, further comprising using the generated color similarity measurement to select a color for printing.

15. The method of claim 6, further comprising using the generated color similarity measurement for at least one of color reproduction, color palette construction, image retrieval, and color profile creation.

16. A computer-readable storage medium storing computer executable instructions for controlling a computer to perform a method comprising:

receiving at least a pair of initial color representations;

selecting a set of lexical color classifiers;

transforming each of the at least a pair of initial color representations into values within the set of lexical color classifiers, wherein each of the initial color has an initial color attribute value that is transformed into lexical color attribute values for each of the lexical color classifiers and wherein the initial color attribute values have n number of color dimensions and the set of lexical color classifiers have m number of color dimensions, wherein n is less than m;

calculating color similarity based on values within the set of lexical color classifiers; and

generating a relative similarity measurement of the at least a pair of initial color representations.

17. The computer-readable storage medium of claim 16, wherein the set of lexical color classifiers is selected based on the initial color representations.

18. The computer-readable storage medium of claim 16, wherein generating the relative similarity measurement is performed using cosine similarity.

19. The computer-readable storage medium of claim 16, wherein the method further comprises determining if the relative similarity measurement indicates a match.

20. The computer-readable storage medium of claim 19, wherein the relative similarity measurement is determined to indicate a match if the relative similarity measurement is between 0 and 1.