Metric-based recognition, systems and methods

Patent metadata

Field	Value
Publication number	US-10121092-B2
Application number	US-201715785932-A
Country	US
Kind code	B2
Filing date	Oct 17, 2017
Priority date	Aug 19, 2013
Publication date	Nov 6, 2018
Grant date	Nov 6, 2018

Abstract

Apparatus, methods and systems of object recognition are disclosed. Embodiments of the inventive subject matter generates map-altered image data according to an object-specific metric map, derives a metric-based descriptor set by executing an image analysis algorithm on the map-altered image data, and retrieves digital content associated with a target object as a function of the metric-based descriptor set.

First claim

What is claimed is:

1. A method of generating a metric-based recognition map comprising:
receiving, by a computing device configured to operate as an image processing engine, image data;
compiling, by the image processing engine, an initial object-specific metric map for a specific human person from at least a portion of the image data where the portion represents at least a portion of the object;
generating, by the image processing engine, a metric-based descriptor set by executing an image analysis algorithm on the portion of the image data as a function of the initial object-specific metric map; and
storing the metric-based descriptor set in an object recognition database.

2. The method of claim 1 , further comprising adjusting the initial object-specific metric map to generate a new object-specific metric map by tuning metric values in a manner effective to enhance differentiation of descriptors generated by the image analysis algorithm as executed on the portion of the image data.

3. The method of claim 2 , wherein adjusting the initial object-specific metric map includes accepting user input that alters at least some metric values within the initial object-specific metric map.

4. The method of claim 2 , wherein adjusting the initial object-specific metric map includes the image processing engine recommending at least one a metric value that increases a confidence of a descriptor.

5. The method of claim 2 , wherein adjusting the initial object-specific metric map includes the image processing engine automatically adjusting metric values of the initial object-specific metric map.

6. The method of claim 2 , wherein the new metric-based map comprises a non-linear mapping from metric values within the initial metric-based map.

7. The method of claim 1 , further comprising generating an object-specific color map based the object-specific metric map.

8. The method of claim 7 , further comprising storing the object-specific color map as part of the metric-based descriptor set.

9. The method of claim 1 , further comprising identifying at least one of a position and an orientation of an imaging device configured to capture the image data.

10. The method of claim 9 , further comprising storing the at least one of the position and the orientation with the metric-based descriptor set.

11. The method of claim 1 , further comprising removing specularity from the image data.

12. The method of claim 1 , wherein the object-specific metric map comprises a pixel-level metric map.

13. The method of claim 1 , wherein the metric-based descriptor set comprises lighting invariant descriptors.

14. The method of claim 1 , wherein the metric-based descriptor set comprises metric-based invariant descriptors.

15. The method of claim 14 , wherein the metric-based descriptors comprise metric-based scale invariant descriptors.

16. The method of claim 1 , wherein the object comprises a physical object.

17. The method of claim 1 , further comprising storing a key frame bundle that includes the metric-based descriptor set.

18. The method of claim 1 , wherein the map is focused on skin tone.

19. The method of claim 1 , wherein the map comprises a tissue-specific map.

20. The method of claim 18 , further comprising identifying skin tone variations of a specific person's face that are indicative of a skin lesion or other abnormality.

21. The method of claim 19 , further comprising one or more tissue-specific maps that aid in differentiating structure or features of internal organs during surgery.

22. The method of claim 21 , wherein one or more features such as tumors are identified because such features fail to conform to the person's tissue-specific maps.

23. A non-transitory computer readable medium storing instructions executable on a processor for processing image data to generate a metric-based recognition map, the instructions comprising instructions to:
compile an initial object-specific metric map for a specific human person from at least a portion of the image data where the portion represents at least a portion of the object;
generate a metric-based descriptor set by executing an image analysis algorithm on the portion of the image data as a function of the initial object-specific metric map; and
store the metric-based descriptor set in an object recognition database.

24. A device for generating a metric-based recognition map comprising:
a computing device configured to operate as an image processing engine, the image processing engine configured to:
receive image data;
compile an initial object-specific metric map for a specific human person from at least a portion of the image data where the portion represents at least a portion of the object;
generate a metric-based descriptor set by executing an image analysis algorithm on the portion of the image data as a function of the initial object-specific metric map; and
store the metric-based descriptor set in an object recognition database.

Assignees

• Nant Holdings Ip Llc

Inventors

• Siddiqui Matheen

Classifications

• G06V10/56

  relating to colour · CPC title

• G06F16/3331

  Query processing · CPC title

• G06F16/51

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/785

  using colour or luminescence · CPC title

• G06F16/907

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title