Image processing based on scene recognition

Patent metadata

Field	Value
Publication number	US-9426385-B2
Application number	US-201514616634-A
Country	US
Kind code	B2
Filing date	Feb 6, 2015
Priority date	Feb 7, 2014
Publication date	Aug 23, 2016
Grant date	Aug 23, 2016

Abstract

Digital image processing is described that enables live prevention of recording and/or displaying of unwanted images. A device for processing a time sequence of images is provided. The device is configured to: retrieve an image of the time sequence of images from a memory; perform scene recognition on the retrieved image; and perform an action on the retrieved image, based upon the result of the scene recognition, before the images of the time sequence of images are recorded, displayed, and/or stored. The retrieval of the image, the performance of the scene recognition, and the performance of the action can be performed in real-time. The action can include at least one of adapting at least a part of retrieved image, modifying the retrieved image, preventing storage of the retrieved image, preventing a display of the retrieved image, erasing the retrieved image, or encrypting the retrieved image.

First claim

What is claimed is:

1. A system for processing a time sequence of images, the system comprising:
a processor; and
a memory coupled to the processor for storing instructions, which when executed from the memory, cause the processor to perform operations for processing the time sequence of images, the operations including:
retrieving an image of the time sequence of images from the memory, wherein the time sequence of images is temporarily stored in the memory;
performing scene recognition on the retrieved image, wherein the scene recognition comprises at least one of recognizing a scene, recognizing objects in the scene, and recognizing an event in the scene;
applying an identifier to the retrieved image after the scene recognition is performed, wherein the identifier applied to the retrieved image correlates to a result of the scene recognition; and
performing an action on the retrieved image, based on matching the identifier to a predefined identifier, before the images of the time sequence of images are at least one of recorded, displayed, and stored.

2. The system of claim 1 , wherein the action includes at least one of adapting at least a part of retrieved image, modifying the retrieved image, preventing the retrieved image from being stored in a data storage, preventing the retrieved image from being displayed on a display device, erasing the retrieved image from the memory, or encrypting the retrieved image.

3. The system of claim 1 , wherein the performance of scene recognition includes processing the retrieved image using at least one scene recognition algorithm.

4. The system of claim 3 , wherein the processing includes identifying at least one of a setting, an object, or an event in the retrieved image.

5. The system of claim 4 , wherein the system further comprises:
after processing the identification of the retrieved image, applying the identifier to at least one of the setting, the object, or the event in the retrieved image after the scene recognition is performed.

6. The system of claim 5 , wherein the identifier includes at least one of a number, a letter, a label, or a hash function.

7. The system of claim 1 , wherein the retrieval of the image, the performance of the scene recognition on the retrieved image, and the performance of the action on the retrieved image are performed in real-time.

8. The system of claim 7 , wherein each image of the time sequence of images is retrieved, subjected to the scene recognition, and subjected to the action in a sequential order.

9. The system of claim 7 , wherein each n th image of the time sequence of images is retrieved, subjected to the scene recognition, and subjected to the action.

10. A non-transitory computer-readable medium storing instructions which, when executed by one or more processors in a processing device, cause the processing device to perform a method for processing a time sequence of images, the method comprising:
retrieving an image of the time sequence of images from a memory, wherein the time sequence of images is temporarily stored in the memory;
performing scene recognition on the retrieved image, wherein the scene recognition comprises at least one of recognizing a scene, recognizing objects in the scene, and recognizing an event in the scene;
applying an identifier to the retrieved image after the scene recognition is performed, wherein the identifier applied to the retrieved image correlates to a result of the scene recognition; and
performing an action on the retrieved image, based on matching the identifier to a predefined identifier, before the images of the time sequence of images are at least one of recorded, displayed, and stored.

11. The non-transitory computer-readable medium of claim 10 , wherein the action includes at least one of adapting at least a part of retrieved image, modifying the retrieved image, preventing the retrieved image from being stored in a data storage, preventing the retrieved image from being displayed on a display device, erasing the retrieved image from the memory, or encrypting the retrieved image.

12. The non-transitory computer-readable medium of claim 10 , wherein the performance of scene recognition includes processing the retrieved image using at least one scene recognition algorithm.

13. The non-transitory computer-readable medium of claim 12 , wherein the processing includes identifying at least one of a setting, an object, or an event in the retrieved image.

14. The non-transitory computer-readable medium of claim 13 , wherein the method further comprises:
after processing the identification of the retrieved image, applying the identifier to at least one of the setting, the object, or the event in the retrieved image after the scene recognition is performed.

15. The non-transitory computer-readable medium of claim 14 , wherein the identifier includes at least one of a number, a letter, a label, or a hash function.

16. The non-transitory computer-readable medium of claim 10 , wherein the retrieval of the image, the performance of the scene recognition on the retrieved image, and the performance of the action on the retrieved image are performed in real-time.

17. The non-transitory computer-readable medium of claim 16 , wherein each image of the time sequence of images is retrieved, subjected to the scene recognition, and subjected to the action in a sequential order.

18. The non-transitory computer-readable medium of claim 16 , wherein each n th image of the time sequence of images is retrieved, subjected to the scene recognition, and subjected to the action.

19. A computer-implemented method for processing a time sequence of images, the method comprising:
retrieving an image of the time sequence of images from a memory, wherein the time sequence of images is temporarily stored in the memory;
performing scene recognition on the retrieved image, wherein the scene recognition comprises at least one of recognizing a scene, recognizing objects in the scene, and recognizing an event in the scene;
applying an identifier to the retrieved image after the scene recognition is performed, wherein the identifier applied to the retrieved image correlates to a result of the scene recognition; and
performing an action on the retrieved image, based on matching the identifier to a predefined identifier, before the images of the time sequence of images are at least one of recorded, displayed, and stored.

20. The computer-implemented method of claim 19 , wherein the retrieval of the image, the performance of the scene recognition on the retrieved image, and the performance of the action on the retrieved image are performed in real-time.

Assignees

• Euclid Vision Tech B V
• Qualcomm Technologies Inc

Inventors

• Stokman Henricus Meinardus Gerardus

Classifications

• H04N23/667

  Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes · CPC title

• H04N23/611

  where the recognised objects include parts of the human body · CPC title

• H04N5/2621 Primary

  Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability · CPC title

• H04N5/23245

  Electricity · mapped topic

• G06K9/00664

  Physics · mapped topic