Image classification using color profiles

Patent metadata

Field	Value
Publication number	US-12217522-B2
Application number	US-202217664284-A
Country	US
Kind code	B2
Filing date	May 20, 2022
Priority date	Mar 31, 2020
Publication date	Feb 4, 2025
Grant date	Feb 4, 2025

Abstract

A device may receive a target document. The device may segment the target document into multiple segments. The device may determine, for each segment of the multiple segments, a set of color parameters for a corresponding set of pixels included in that segment. The device may determine, for each segment of the multiple segments, an average color parameter for that segment based on the set of color parameters for the corresponding set of pixels included in that segment. The device may generate a target color profile for the target document based on determining the average color parameter for each segment. The device may compare the target color profile and a model color profile associated with classifying the target document. The device may classify the target document based on comparing the target color profile and the model color profile.

First claim

What is claimed is:

1. A method, comprising:
generating, by a device, a target color profile for a target document based on determining an average color parameter for a segment associated with the target color profile;
determining, by the device, whether the target color profile satisfies a matching condition with respect to a model color profile,
wherein the matching condition is satisfied when the average color parameter, is within a respective threshold tolerance of a corresponding average color parameter included in a model set of average color parameters of one or more model sets of average color parameters associated with corresponding segments for document classification; and

classifying, by the device, the target document based on determining whether the target color profile satisfies the matching condition.

2. The method of claim 1 , wherein generating the target color profile further comprises:
segmenting the target document into one or more segments including the segment associated with the target color profile.

3. The method of claim 1 , wherein generating the target color profile comprises:
determining a color profile for each pixel in the segment associated with the target color profile, and
determining the average color parameter based one determining the color profile for each pixel in the segment associated with the target color profile.

4. The method of claim 1 , wherein determining whether the target color profile satisfies the matching condition comprises:
determining the target color profile satisfies the matching condition using a tolerance vector.

5. The method of claim 1 , further comprising:
comparing the target color profile to a model color profile associated with a different orientation.

6. The method of claim 1 , wherein classifying the target document comprises:
classifying the target document with a document type associated with the model color profile.

7. The method of claim 1 , further comprising:
generating the model color profile.

8. A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
generate a target color profile for a target document based on determining an average color parameter for a segment associated with the target color profile;
determine whether the target color profile satisfies a matching condition with respect to a model color profile,
wherein the matching condition is satisfied when the average color parameter, is within a respective threshold tolerance of a corresponding average color parameter included in a model set of average color parameters of one or more model sets of average color parameters associated with corresponding segments for document classification; and

classify the target document based on determining whether the target color profile satisfies the matching condition.

9. The device of claim 8 , wherein the one or more processors, to generate the target color profile, are configured to:
segment the target document into one or more segments including the segment associated with the target color profile, and
determine the average color parameter for the segment associated with the target color profile.

10. The device of claim 8 , wherein the one or more processors, to generate the target color profile, are configured to:
determine a color profile for each pixel in the segment associated with the target color profile, and
determine the average color parameter based one determining the color profile for each pixel in the segment associated with the target color profile.

11. The device of claim 8 , wherein the one or more processors, to determine whether the target color profile satisfies the matching condition, are configured to:
determine the target color profile satisfies the matching condition using a tolerance vector.

12. The device of claim 8 , wherein the one or more processors are further configured to:
compare the target color profile to a model color profile associated with a different orientation.

13. The device of claim 8 , wherein the one or more processors, to classify the target document, are configured to:
classify the target document with a document type associated with the model color profile.

14. The device of claim 8 , wherein the one or more processors are further configured to:
generate the model color profile.

15. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
generate a target color profile for a target document based on determining an average color parameter for a segment associated with the target color profile;
determine whether the target color profile satisfies a matching condition with respect to a model color profile,
wherein the matching condition is satisfied when the average color parameter, is within a respective threshold tolerance of a corresponding average color parameter included in a model set of average color parameters of one or more model sets of average color parameters associated with corresponding segments for document classification; and

classify the target document based on determining whether the target color profile satisfies the matching condition.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to generate the target color profile, cause the device to:
determine a color profile for each pixel in the segment associated with the target color profile, and
determine the average color parameter based one determining the color profile for each pixel in the segment associated with the target color profile.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to determine whether the target color profile satisfies the matching condition, cause the device to:
determine the target color profile satisfies the matching condition using a tolerance vector.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:
compare the target color profile to a model color profile associated with a different orientation.

19. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to classify the target document, cause the device to:
classify the target document with a document type associated with the model color profile.

20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:
generate the model color profile.

Assignees

• Capital One Services Llc

Inventors

• Sickert Thomas

Classifications

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06V10/56

  relating to colour · CPC title

• G06T7/90

  Determination of colour characteristics · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06V30/413 Primary

  Classification of content, e.g. text, photographs or tables · CPC title