Methods and systems for content processing

• US 8,503,791 B2
• Filed: 01/09/2012
• Issued: 08/06/2013
• Est. Priority Date: 08/19/2008
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Conwell, William Y.
• Primary Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US13/345,983
• Publication Number:
  US 20120114249A1
• Time in Patent Office: 575 Days
• Field of Search: 382/100, 382/181, 382/182, 382/190, 382/195, 382224-231, 707722-757
• US Class Current: 382/190
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2215/00 Indexing scheme for image rendering
• CPC Class Codes: G06T 3/00 Geometric image transformations in the plane of the image
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: H04N 1/00307 with a mobile telephone apparatus constructional features of portable telephone sets H04M1/0202; mobile radio systems H04W84/00
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/3278 Transmission
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

Cell phones and other portable devices are equipped with a variety of technologies by which existing functionality can be improved, and new functionality can be provided. Some relate to visual search capabilities, and determining appropriate actions responsive to different image inputs. Others relate to processing of image data. Still others concern metadata generation, processing, and representation. Yet others relate to coping with fixed focus limitations of cell phone cameras, e.g., in reading digital watermark data. Still others concern user interface improvements. A great number of other features and arrangements are also detailed.

Claims

1. A method comprising:

receiving a first image captured by a camera-equipped device, the first image depicting a subject from a geolocation;

by reference to said geolocation, identifying plural textual descriptors related to the first image;

processing said textual descriptors in discerning whether the first image depicts a subject that is likely of a first class or a second class, said processing being performed by one or more hardware processors configured to perform such act; and

taking an action dependent on whether the first image depicts a subject that is likely of the first class or the second class.

2. The method of claim 1 in which the identifying includes collecting metadata associated with plural other images from said geolocation, and using said collected metadata as said textual descriptors.

3. The method of claim 2 that includes:

for each of said other images, categorizing said other image as most likely belonging to said first or second class, said categorizing including processing metadata associated with said other image, said categorizing resulting in a first group of plural images that most likely belong to the first class, and a second group of plural images that most likely belong to the second class;

identifying a first visual feature that characterizes plural images in the first group;

identifying a second, different, visual feature that characterizes plural images in the second group;

evaluating the first image for the first and second visual features; and

employing a result of said evaluating in discerning a class of the subject depicted in the first image.

4. The method of claim 3 in which identifying the first visual feature comprises:

evaluating plural images in the first group for a first candidate image feature;

evaluating plural images in the first group for a second candidate image feature;

assessing results of said evaluations for clustering; and

identifying the first visual feature to be the first candidate image feature, based on a result of said assessing.

5. The method of claim 1 that includes processing said textual descriptors by comparing with a glossary of place-related terms.

6. The method of claim 1 that includes processing said textual descriptors by comparing with a glossary of people-related terms.

7. The method of claim 1 that includes determining a first score indicating a likelihood that the first image depicts a subject of the first class, and determining a second score indicating a likelihood that the first image depicts a subject of the second class.

8. The method of claim 1 that includes:

collecting metadata associated with plural other images from said geolocation, and using said collected metadata as said textual descriptors; and

for each of said other images, discerning a first likelihood that such other image depicts a subject of the first class, and discerning a second likelihood that such other image depicts a subject of the second class, said discerning including processing textual descriptors associated with such other image.

9. The method of claim 1 that includes:

processing said textual descriptors in discerning whether the first image depicts a subject that is likely of a first class or a second class or a third class; and

taking an action dependent on whether the first image depicts a subject that is likely of the first class or the second class or the third class.

10. The method of claim 9 in which one of said classes comprises a person class, and another of said classes comprises a place class.

11. One or more non-transitory computer readable media having instructions stored therein that cause a computer device programmed by said instructions to perform a method that includes:

receiving a first image, the first image depicting a subject from a geolocation;

by reference to said geolocation, identifying plural textual descriptors related to the first image;

processing said textual descriptors in discerning whether the first image depicts a subject that is likely of a first class or a second class; and

taking an action dependent on whether the first image depicts a subject that is likely of the first class or the second class.

12. The media of claim 11 in which said method includes collecting metadata associated with plural other images from said geolocation, and using said collected metadata as said textual descriptors.

13. The media of claim 12 in which said method includes:

for each of said other images, categorizing said other image as most likely belonging to said first or second class, said categorizing including processing metadata associated with said other image, said categorizing resulting in a first group of plural images that most likely belong to the first class, and a second group of plural images that most likely belong to the second class;

identifying a first visual feature that characterizes plural images in the first group;

identifying a second, different, visual feature that characterizes plural images in the second group;

evaluating the first image for the first and second visual features; and

employing a result of said evaluating in discerning a class of the subject depicted in the first image.

14. The media of claim 13 in which said identifying the first visual feature comprises:

evaluating plural images in the first group for a first candidate image feature;

evaluating plural images in the first group for a second candidate image feature;

assessing results of said evaluations for clustering; and

identifying the first visual feature to be the first candidate image feature, based on a result of said assessing.

15. The media of claim 11 in which said method includes processing said textual descriptors by comparing with a glossary of place-related terms.

16. The media of claim 11 in which said method includes processing said textual descriptors by comparing with a glossary of people-related terms.

17. The media of claim 11 in which said method includes determining a first score indicating a likelihood that the first image depicts a subject of the first class, and determining a second score indicating a likelihood that the first image depicts a subject of the second class.

18. The media of claim 11 in which said method includes:

collecting metadata associated with plural other images from said geolocation, and using said collected metadata as said textual descriptors; and

for each of said other images, discerning a first likelihood that such other image depicts a subject of the first class, and discerning a second likelihood that such other image depicts a subject of the second class, said discerning including processing textual descriptors associated with such other image.

19. The media of claim 11 in which said method includes:

processing said textual descriptors in discerning whether the first image depicts a subject that is likely of a first class or a second class or a third class; and

taking an action dependent on whether the first image depicts a subject that is likely of the first class or the second class or the third class.

20. A portable device that includes a camera, a processor and a memory, the memory containing instructions for programming the processor to cause the device to perform acts including:

receive a first image, the first image depicting a subject from a geolocation;

by reference to said geolocation, identify plural textual descriptors related to the first image;

process said textual descriptors in discerning whether the first image depicts a subject that is likely of a first class or a second class; and

take an action dependent on whether the first image depicts a subject that is likely of the first class or the second class.