System and process for automatically finding objects of a specific color

• US 10,127,688 B2
• Filed: 07/17/2017
• Issued: 11/13/2018
• Est. Priority Date: 01/24/2011
• Status: Active Grant

• Current Assignee: Syte - Visual Conception, Ltd.
• Original Assignee: Alon Atsmon, Dan Atsmon
• Inventors: Atsmon, Alon, Atsmon, Dan
• Primary Examiner(s): Bayat, Ali
• Application Number:
  US15/650,993
• Publication Number:
  US 20170316584A1
• Time in Patent Office: 484 Days
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H05K 999/99 dummy group

Abstract

A computer implemented method, system and computer program product for identifying the Main Colors and the matching colors of a visual object, and then viewing on a mobile device select items comprising the matching colors, such as from a merchant'"'"'s catalog. A visual object is analyzed for color content, and the results are stored on a system database located on the device or on a remote server. The color analysis of the objects comprise advanced image processing techniques, such as Main Color extraction using color space transformation comprising HSV, RGB and CYMK to map between pixels in the image. The user can subsequently view a display on their mobile identifying the visual object'"'"'s Main Colors and at least one Harmonic Color; and then select and view all items (i.e. products in a database) comprising one Harmonic Color, and/or all items of a specific type and Harmonic Color.

Claims

1. A computer implemented method for overlaying visual items, comprising,

identifying at least one visual object image captured using a client terminal;

conducting a color analysis to identify at least one main color in said at least one visual object;

sending a message over a computer network for querying an image database managed by a remote server against said at least one main color to select at least one stored image depicting a color matching object having said at least one main color;

receiving said at least one stored image from the remote server as a real time feedback to said querying;

adding said at least one stored image as an overlay on top of at least part of said at least one visual object, the overlay is presented by a display of the client terminal to present said color matching object to a user in association with said at least one visual object.

2. The method of claim 1, wherein said color analysis is conducted to identify color harmonics data, said querying is done against said color harmonics data and said at least one main color.

3. The method of claim 1, further comprising displaying said overlay on top of said at least one visual object on a display of said client terminal.

4. The method of claim 1, wherein said conducting a color analysis comprises determining said main Colors by identifying Base, Primary, Secondary and Tertiary Colors of said visual object.

5. The method of claim 2, further comprising determining said color harmonics data based on a color wheel.

6. The method of claim 2, wherein said color harmonics data comprises a member of a group consisting of:

said visual object'"'"'s Complementary Color, Analogous Colors, Triadic Colors, Split-Complementary Colors, Tetradic Colors, and Square Colors.

7. The method of claim 1, wherein said color analysis comprises separating a visual object from a background in said at least one visual object image for compensating for distortions.

8. The method of claim 1, wherein said color analysis comprises imaging processing techniques selected from the group consisting of:

HSV (Hue, Saturation, Value) color histograms, RGB color histograms, CYMK color histograms, and multi-space color clustering.

9. The method of claim 1, wherein said terminal device is a mobile device and said at least one visual object image are part of a plurality of visual object images continuously captured while said conducting, said querying, and said adding are executed by said device terminal.

10. The method of claim 1, wherein said at least one visual object image images a visual object selected from a group consisting of:

a home furnishing, a clothing item, internal and an external wall covering, and a hair color.

11. The method of claim 1, wherein conducting a color analysis comprises conducting a location analysis of said client terminal to acquire location data generated by a module of said client terminal;

said querying is done against said location data and said at least one main color.

12. The method of claim 1, wherein said querying comprises conducting an analysis of said at least one object to identify a fit between color distributions of said at least one stored image and said at least one visual object.

13. The method of claim 1, wherein said querying comprises conducting an analysis of said at least one object to identify a fit between at least one of texture, shape, and edge histogram of said at least one stored image and said at least one visual object.

14. The method of claim 1, wherein said querying comprises conducting an analysis of said at least one object to identify a face similarity between faces in said at least one stored image and said at least one visual object.

15. A non-transitory computer readable medium having embodied thereon a program, the program being executable by a processor for performing a method for overlaying visual items, the method comprising:

identifying at least one visual object image captured using a client terminal;

conducting a color analysis to identify at least one main color in said at least one visual object;

sending a message over a computer network for querying an image database managed by a remote server against said at least one main color to select at least one stored image depicting a color matching object having said at least one main color;

receiving said at least one stored image from the remote server as a real time feedback to said querying adding said at least one stored image as an overlay on top of at least part of said at least one visual object, the overlay is presented by a display of the client terminal to present said color matching object to a user in association with at least one visual object.

16. An internet connected system for overlaying visual items, comprising:

a server comprising;

an interface adapted for receiving over a computer network from one or more capturing devices at least one visual object image;

an image database storing a plurality of images;

a program store storing code;

a processor coupled to the interface, the image database, and the program store for implementing the stored code, the code comprising;

code instructions for conducting a color analysis to identify at least one main color in said at least one visual object;

code instructions for querying said image database against said at least one main color to select at least one stored image depicting a color matching object having said at least one main color; and

as a real time feedback to said querying adding said at least one stored image as an overlay on top of at least part of said at least one visual object to present said color matching object to a user in association with said at least one main color.

17. The system of claim 16, wherein said processor is adapted for implementing code instructions to determine color harmonics data of said at least one visual object image, wherein said color analysis is based on said color harmonics data.

18. The system of claim 17, wherein said color harmonics data is determined using a color wheel and said color harmonics data comprises a member of a group consisting:

said object'"'"'s Complementary Color, Analogous Colors, Triadic Colors, Split-Complementary Colors, Tetradic Colors, and Square Colors.

19. The system of claim 16, wherein said color analysis comprises, separating in said at least one visual object image at least one visual object from a background for compensating for light distortions.

20. The system of claim 16, wherein said color analysis comprises imaging processing techniques selected from the group consisting of:

HSV (Hue, Saturation, Value) color histograms, RGB color histograms, CYMK color histograms, and multi-space color clustering.