Fast recognition algorithm processing, systems and methods

• US 9,508,009 B2
• Filed: 05/27/2016
• Issued: 11/29/2016
• Est. Priority Date: 07/19/2013
• Status: Active Grant

• Current Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Original Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Inventors: Wnuk, Kamil, Song, Bing, Siddiqui, Matheen, McKinnon, David, Sudol, Jeremi, Soon-Shiong, Patrick, Dialameh, Orang
• Primary Examiner(s): Rahmjoo, Manuchehr
• Application Number:
  US15/167,818
• Publication Number:
  US 20160275353A1
• Time in Patent Office: 186 Days
• Field of Search: 382/190
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20004 Adaptive image processing
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Systems and methods of quickly recognizing or differentiating many objects are presented. Contemplated systems include an object model database storing recognition models associated with known modeled objects. The object identifiers can be indexed in the object model database based on recognition features derived from key frames of the modeled object. Such objects are recognized by a recognition engine at a later time. The recognition engine can construct a recognition strategy based on a current context where the recognition strategy includes rules for executing one or more recognition algorithms on a digital representation of a scene. The recognition engine can recognize an object from the object model database, and then attempt to identify key frame bundles that are contextually relevant, which can then be used to track the object or to query a content database for content information.

Claims

1. A medical image scanning device comprising:

a processor;

a non-transitory, tangible computer readable memory storing software instructions executable by the processor; and

a recognition engine executable on the processor according to the software instructions and that is configurable to;

obtain a digital image comprising a plurality of objects;

determine a recognition strategy from the digital image, the recognition strategy comprising rules for executing at least one recognition algorithm on the digital image;

generate at least one recognition feature by executing the at least one recognition algorithm on the digital image according to the rules;

identify known modeled objects by matching the at least one recognition feature to similar known features of known modeled objects;

identify key frame bundles associated with the known modeled objects, wherein a key frame bundle includes a link to content; and

retrieve content related to the known modeled objects via at least one link in at least one key frame bundle.

2. The medical image scanning device of claim 1, wherein the digital image comprises a scanned image.

3. The medical image scanning device of claim 1, wherein the at least one recognition feature comprises a scale.

4. The medical image scanning device of claim 1, wherein the at least one recognition feature comprises at least one of a shape and an edge.

5. The medical image scanning device of claim 1, wherein the at least one recognition feature is related to a point of interest related to the known modeled objects.

6. The medical image scanning device of claim 1, wherein determination of the recognition strategy depends on a context of the digital image.

7. The medical image scanning device of claim 1, further comprising a camera.

8. The medical image scanning device of claim 7, wherein the recognition engine is further configurable to capture the digital image via the camera.

9. The medical image scanning device of claim 1, wherein the digital image comprises video data.

10. The medical image scanning device of claim 1, wherein the recognition strategy comprises a prioritized ordering of the at least one recognition algorithm.

11. The medical image scanning device of claim 1, wherein the recognition strategy comprises a time-based ordering of the at least one recognition algorithm.

12. The medical image scanning device of claim 1, wherein the recognition strategy includes rules based on feature richness.

13. The medical image scanning device of claim 1, wherein the known modeled objects are grouped based on a classification.

14. The medical image scanning device of claim 1, wherein the content comprises mask data.

15. The medical image scanning device of claim 1, wherein the content comprises text data.

16. The medical image scanning device of claim 1, wherein the content is accessible within an electronic medical record storage.

17. The medical image scanning device of claim 1, wherein the recognition engine is further configurable to identify objects within the digital image via the key frame bundles at a rate of at least 100 objects per second.

18. The medical image scanning device of claim 17, wherein the recognition engine is further configurable to identify objects within the digital image via the key frame bundles at a rate of at least 1000 objects per second.

19. The medical image scanning device of claim 1, wherein the recognition engine is further configurable to differentiate objects within the digital image via the key frame bundles at a rate of at least 100 objects per second.

20. The medical image scanning device of claim 19, wherein the recognition engine is further configurable to differentiate objects within the digital image via the key frame bundles at a rate of at least 1000 objects per second.

21. The medical image scanning device of claim 1, wherein the key frame bundles are contextually relevant to the digital image.