System and method for fine-grained control of privacy from image and video recording devices

• US 9,571,785 B2
• Filed: 04/11/2014
• Issued: 02/14/2017
• Est. Priority Date: 04/11/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Farrell, Robert G, Kozloski, James R, Pickover, Clifford A
• Primary Examiner(s): HARVEY, DAVID E
• Application Number:
  US14/250,935
• Publication Number:
  US 20150296170A1
• Time in Patent Office: 1,040 Days
• Field of Search: 386/254
• US Class Current: 1/1
• CPC Class Codes: G06F 21/602 Providing cryptographic facilities or services
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 2005/91321 the copy protection signal being a copy protection control signal, e.g. a record inhibit signal
• CPC Class Codes: H04N 2005/91335 the copy protection signal being a watermark
• CPC Class Codes: H04N 2005/91357 by modifying the video signal
• CPC Class Codes: H04N 5/913 for scrambling ; for copy protection
• CPC Class Codes: H04N 9/8227 the additional signal being at least another television signal

Abstract

A system and method for fine-grained privacy control of image and video recordings uses a model-based approach to solve privacy issues. The method includes steps of: receiving a digital capture of a subject bound by privacy constraints; receiving information regarding the subject, the environment, and the privacy constraints; using the information to generate a model image of the subject within the environment; associating a disposition tag with an appearance of the subject in the model image; and comparing the model image with the digital capture to determine coordinates in the recording where a privacy control action, such as a blocking action, should be applied.

Claims

1. A method for providing privacy control for digital capture of a recording, said method comprising:

using a processor device, performing;

receiving the digital capture from a recorder, said digital capture comprising the recording of a person within an environment, wherein said person is bound by privacy constraints;

receiving information regarding the environment, the person, and the privacy constraints;

identifying the person within the digital capture based on the received information regarding the person;

generating a model image of the environment including the person by applying the information about the person, the environment, and the privacy constraints;

associating a disposition tag with an identified person in the model image, wherein said disposition tag references a privacy control action to take according to the person'"'"'s privacy constraints;

comparing the model image with the digital capture of the recording; and

determining coordinates in the recording where the privacy control action is to be applied.

2. The method of claim 1 further comprising sending the coordinates to the recorder.

3. The method of claim 1 wherein receiving the information comprises receiving data needed to identify the person from multiple angles.

4. The method of claim 1 wherein the privacy restriction varies according to pre-determined disposition parameters.

5. The method of claim 1 wherein the privacy restriction comprises a restriction selected from a group consisting of:

no recording of the person allowed, recording of the person allowed but with payment, limited resolution recording of the person only, recording of the person allowed at certain time of day, and recording of the person allowed only with credit.

6. The method of claim 3 wherein identifying the person comprises performing a real-time comparison between the data needed to identify the person and the recording to provide a confidence level of an identification of the person.

7. The method of claim 6 wherein identifying the person further comprises increasing the confidence level of the identification through at least one action selected from a group consisting of:

sampling, smoothing the tagged area, increasing the tagged area, decreasing the tagged area, analysis of digital positioning data, and analysis of calendar data.

8. The method of claim 7 wherein the confidence level controls the privacy control action applied to the image.

9. The method of claim 7 wherein the confidence level triggers a signal sent to a crowd-sourcing component to increase the confidence level.

10. The method of claim 1 wherein the privacy control action is selected from a group consisting of:

jamming, applying a low resolution, overlaying the image, encryption, introduction of noise, masking for partial transparency of information, and replacement of image.

11. An information processing system for providing privacy control for digital capture of a recording, comprising:

a processor device; and

a memory operably coupled with the processor device, said memory comprising computer-executable instructions causing a computer to perform;

receiving the digital capture from a recorder, said digital capture comprising the recording of a person within an environment, wherein said person is bound by privacy constraints;

receiving information regarding the environment, the person, and the privacy constraints;

identifying the person within the digital capture based on the received information regarding the person;

generating a model image of the environment including the person by applying the information about the person, the environment, and the privacy constraints;

associating a disposition tag with an identified person in the model image, wherein said disposition tag references a privacy control action to take according to the person'"'"'s privacy constraints;

comparing the model image with the digital capture of the recording; and

determining coordinates in the recording where the privacy control action is to be applied.

12. The information processing system of claim 11 wherein the recording is an audio recording.

13. The information processing system of claim 11 wherein the computer-executable instructions further cause the computer to perform:

applying the privacy control action to the recording.

14. The information processing system of claim 13 wherein applying the privacy control action comprises applying a data overlay to at least a portion of the person in the recording.

15. The information processing system of claim 11 wherein the privacy restriction comprises a restriction selected from a group consisting of:

no recording of the person allowed, recording of the person allowed but with payment, limited resolution recording of the person only, recording of the person allowed at certain time of day, and recording of the person allowed only with credit.

16. The information processing system of claim 11 wherein identifying the person further comprises increasing a confidence level of the identification through at least one action selected from a group consisting of:

sampling, smoothing the tagged area, increasing the tagged area, decreasing the tagged area, analysis of digital positioning data, and analysis of calendar data.

17. The information processing system of claim 16 wherein the confidence level controls the privacy control action applied to the recording.

18. A computer program product comprising a non-transitory computer-readable storage medium with computer-executable instructions for providing privacy control for digital capture of a recording stored thereon, said computer-executable instructions comprising:

receiving the digital capture from a recorder, said digital capture comprising the recording of a person within an environment, wherein said person is bound by privacy constraints;

receiving information regarding the environment, the person, and the privacy constraints;

identifying the person within the digital capture based on the received information regarding the person;

generating a model image of the environment including the person by applying the information about the person, the environment, and the privacy constraints;

associating a disposition tag with an identified person in the model image, wherein said disposition tag references a privacy control action to take according to the person'"'"'s privacy constraints;

comparing the model image with the digital capture of the recording; and

determining coordinates in the recording where the privacy control action is to be applied.

19. The computer program product of claim 18 wherein the privacy restriction comprises a restriction selected from a group consisting of:

no recording of the person allowed, recording of the person allowed but with payment, limited resolution recording of the person only, recording of the person allowed at certain time of day, and recording of the person allowed only with credit.

20. The computer program product of claim 18 wherein identifying the person further comprises increasing a confidence level of the identification through at least one action selected from a group consisting of:

sampling, smoothing the tagged area, increasing the tagged area, decreasing the tagged area, analysis of digital positioning data, and analysis of calendar data.