System and method for normalization and codification of colors for dynamic analysis

• US 8,600,153 B2
• Filed: 06/05/2013
• Issued: 12/03/2013
• Est. Priority Date: 02/07/2012
• Status: Active Grant

• Current Assignee: Zencolor Global, LLC
• Original Assignee: Zencolor Corporation
• Inventors: Gershon, Dann, Robinson, David, Wilder, Jonathan, Schonfeld, Maurice W.
• Primary Examiner(s): Krasnic, Bernard
• Application Number:
  US13/910,557
• Publication Number:
  US 20130266217A1
• Time in Patent Office: 181 Days
• Field of Search: 382/162, 382/164, 382/165, 382/170, 382/190, 707/741
• US Class Current: 382/162
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06Q 30/0639 Item locations
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G09G 5/06 using colour palettes, e.g. look-up tables

Abstract

A system and method for normalizing and codifying divergent color systems into a single universal color system. The middleware engine receives a data feed comprising a plurality of color swatches or images from one or more merchant system and normalizes the data feed into a common format. The dominant processor extracts the product images from the normalized data, segments each product image into segments, determines a dominant color for each segment, and determines the dominant product color for each product image based on prevalence of the dominant product color in each segment. The matched color processor converts the determined dominant product color into a digital value of the universal color system based on the color component intensity values.

Claims

1. A computer based method for normalizing and codifying divergent color systems into a single universal color system, comprising the steps of:

receiving a data feed comprising a plurality of color swatches or images from a merchant system by a middleware engine of a server over a communications network;

normalizing the data feed into a common format by the middleware engine;

extracting image data comprising a plurality of product images from the normalized data feed;

segmenting each product image into a plurality of segments by an image segmentation processor;

analyzing each segment to determine a dominant color for said each segment by a dominant color processor;

determining at least one dominant product color for said each product image based on prevalence of said at least one dominant product color in said each segment by the dominant color processor;

converting said at least one dominant product color to a digital value of the universal color system based on color component intensity values by a matched color processor;

assigning a hexadecimal code of the universal color system to said each product image that is closest to the digital value of said each product image by the matched color processor; and

storing the data feed, said each product image, said each segment of said each product image, the dominant color for said each segment, said at least one product dominant color for said each product image, and the digital value and the hexadecimal code of said each product image in a database by the server.

2. The method of claim 1, further comprising the steps of determining an Euclidian distance between the digital value and each hexadecimal code of the universal color system based on their color component intensity values;

and assigning the hexadecimal code yielding a shortest Euclidian distance to said each product image by the matched color processor.

3. The method of claim 1, further comprising the steps of receiving data feeds from a plurality of merchant systems by the middleware engine over said communications network, and generating a product database from data feed received from said plurality of merchant systems indexed and searchable by color based queries.

4. The method of claim 3, wherein the step of normalizing comprises the step of depersonalizing the data feeds received from the merchant systems to remove merchant or consumer identifying information by the middleware engine.

5. The method of claim 1, further comprising the step of dividing said each segment until only one dominant color is identified in a subdivision by the image segmentation processor.

6. The method of claim 1, further comprising the steps of generating a color histogram of dominant colors for said each segment;

and generating a parseable ordered list of dominant colors for said each segment from the color histogram by the dominant color processor.

7. The method of claim 1, further comprising the step of determining the dominant color of said each segment on a pixel by pixel basis by the dominant color processor, the color appearing most frequently across all pixels being designated as the dominant color of said each segment.

8. The method of claim 1, further comprising the steps of extracting a pattern from said each segment, and comparing the extracted pattern to a predefined set of patterns stored in said database by a pattern identification processor to determine a product pattern.

9. The method of claim 8, further comprising the step of categorizing the pattern in said each segment by determining proximity and frequency of two or more colors within said each segment by the pattern identification processor.

10. A system for normalizing and codifying divergent color systems into a single universal color system, comprising:

a server connected to a communications system for receiving, processing and codifying divergent color data from a merchant system, the server comprising;

a middleware engine for receiving a data feed comprising a plurality of color swatches or images from said merchant system, and normalizing the data feed into a common format;

an image segmentation processor for extracting image data comprising a plurality of product images from the normalized data feed, and segmenting each product image into a plurality of segments;

a dominant color processor for analyzing each segment to determine a dominant color for said each segment, and determining at least one dominant product color for said each product image based on prevalence of said at least one dominant product color in said each segment; and

a matched color processor for converting said at least one dominant product color to a digital value of the universal color system based on color component intensity values, and assigning a hexadecimal code of the universal color system to said each product image that is closest to the digital value of said each product image; and

a database for storing the data feed, said each product image, said each segment of said each product image, the dominant color for said each segment, said at least one dominant product color for said each product image, and the digital value and the hexadecimal code of said each product image.

11. The system of claim 10, wherein the matched color processor determines an Euclidian distance between the digital value and each hexadecimal code of the universal color system based on their color component intensity values, and assigns the hexadecimal code yielding a shortest Euclidian distance to said each product image.

12. The system of claim 10, wherein the middleware engine receives data feeds from a plurality of merchant systems;

and wherein the server generates a product database from the data feeds received from said merchant systems indexed and searchable by color based queries.

13. The system of claim 12, wherein the middleware engine depersonalizes the data feeds received from the merchant systems to remove merchant or consumer identifying information.

14. The system of claim 10, wherein the image segmentation processor divides said each segment until only one dominant color is identified in a subdivision.

15. The system of claim 10, wherein the dominant color processor generates a color histogram of dominant colors for said each segment, and a parseable ordered list of dominant colors for said each segment from the color histogram.

16. The system of claim 10, wherein the dominant color processor determines the dominant color of said each segment on a pixel by pixel basis, the color appearing most frequently across all pixels being designated as the dominant color of said each segment.

17. The system of claim 10, wherein the server further comprises a pattern identification processor for extracting a pattern from said each segment, and comparing the extracted pattern to a predefined set of patterns stored in said database to determine a product pattern.

18. The system of claim 17, wherein the pattern identification processor categorizes the pattern in said each segment by determining proximity and frequency of two or more colors within said each segment.

19. A non-transitory computer readable medium comprising computer executable code for normalizing and codifying divergent color systems into a single universal color system, the computer executable code comprising instructions for:

receiving a data feed comprising a plurality of color swatches or images from a merchant system by a middleware engine of a server over a communications network;

normalizing the data feed into a common format by the middleware engine;

extracting image data comprising a plurality of product images from the normalized data feed;

segmenting each product image into a plurality of segments by an image segmentation processor;

analyzing each segment to determine a dominant color for said each segment by a dominant color processor;

determining at least one dominant product color for said each product image based on prevalence of said at least one dominant product color in said each segment by the dominant color processor;

converting said at least one dominant product color to a digital value of the universal color system based on color component intensity values by a matched color processor;

assigning a hexadecimal code of the universal color system to said each product image that is closest to the digital value of said each product image by the matched color processor; and

storing the data feed, said each product image, said each segment of said each product image, the dominant color for said each segment, said at least one dominant product color for said each product image, and the digital value and the hexadecimal code of said each product image in a database by the server.

20. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for determining an Euclidian distance between the digital value and each hexadecimal code of the universal color system based on their color component intensity values;

and assigning the hexadecimal code yielding a shortest Euclidian distance to said each product image by the matched color processor.

21. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for receiving data feeds from a plurality of merchant systems by the middleware engine, and generating a product database from the data feeds received from said plurality of merchant systems indexed and searchable by color based queries.

22. The non-transitory computer readable medium of claim 21, wherein said computer executable code further comprises instructions for depersonalizing the data feeds received from the merchant systems to remove merchant or consumer identifying information by the middleware engine.

23. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for dividing said each segment until only one dominant color is identified in a subdivision by the image segmentation processor.

24. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for generating a color histogram of dominant colors for said each segment;

and generating a parseable ordered list of dominant colors for said each segment from the color histogram by the dominant color processor.

25. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for determining the dominant color of said each segment on a pixel by pixel basis by the dominant color processor, the color appearing most frequently across all pixels being designated as the dominant color of said each segment.

26. The non-transitory computer readable medium of claim 19, wherein said computer executable code further comprises instructions for extracting a pattern from said each segment, and comparing the extracted pattern to a predefined set of patterns stored in said database by a pattern identification processor to determine a product pattern.

27. The non-transitory computer readable medium of claim 26, wherein said computer executable code further comprises instructions for categorizing the pattern in said each segment by determining proximity and frequency of two or more colors within said each segment by the pattern identification processor.