Privacy protection in captured image for distribution

• US 10,586,070 B2
• Filed: 11/14/2017
• Issued: 03/10/2020
• Est. Priority Date: 11/14/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cai, Jing, Deng, Yuan Yao, Jia, Yuan Yuan J., Liu, Jing
• Primary Examiner(s): Perungavoor, Venkat
• Application Number:
  US15/811,898
• Publication Number:
  US 20190147185A1
• Time in Patent Office: 847 Days
• Field of Search: None
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/6245 Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G06F 21/6254 by anonymising data, e.g. decorrelating personal data from the owner's identification
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

Providing privacy protection in a captured image includes obtaining the captured image and image coordinates associated with one or more target individuals within the captured image. Facial recognition processing is executed against individual faces within the captured image, and one or more target individuals in the captured image are identified from the image coordinates. Representative data of the one or more target individuals is saved to a whitelist, and a privacy protected version of the captured image may be provided. The privacy protected version of the captured image has one or more altered image features associated with one or more other individuals within the captured image then the one or more target individuals.

Claims

1. A computer-implemented method comprising:

obtaining multiple image frames captured via a user device;

obtaining image coordinates associated with one or more user-selected, target individuals within an image frame of the multiple image frames, the image coordinates including user-device-generated image coordinates for the one or more user-selected, target individuals in the image frame, and being absent coordinates for one or more other non-user-selected individuals in the image frame;

executing facial recognition processing against individual faces within the image frame of the multiple image frames;

identifying the one or more target individuals in the image frame from the received image coordinates;

saving representative data of the one or more target individuals to a whitelist; and

producing a privacy protected version of at least one image frame of the multiple image frames, wherein the privacy protected version of the at least one image frame has one or more altered image features associated with the one or more other individuals within the at least one image frame.

2. The computer-implemented method of claim 1, wherein the obtaining image coordinates associated with the one or more target individuals within the captured image frame comprises receiving image coordinates derived from a user input through a touch screen of the user device, the user input having selected the one or more target individuals.

3. The computer-implemented method of claim 1, further comprising processing the at least one image frame with reference to the whitelist absent the identifying and the saving for the at least one image frame to identify the one or more target individuals within the at least one image frame.

4. The computer-implemented method of claim 1, wherein saving the representative data comprises clipping, at least, individual faces of the one or more target individuals within the image frame as facial images and saving the facial images to the whitelist.

5. The computer-implemented method of claim 1, wherein the one or more altered image features comprise blurred facial images of the one or more other individuals within the image frame.

6. The computer-implemented method of claim 1, further comprising distributing the privacy protected version of the at least one image frame with the one or more altered image features associated with the one or more other individuals within the at least one image frame.

7. The computer-implemented method of claim 1, wherein the multiple image frames are image frames of streaming video.

8. A system for providing privacy protection in a captured image, the system comprising:

a memory; and

a processing circuit communicatively coupled to the memory, wherein the system performs a method comprising;

obtaining multiple image frames captured via a user device;

obtaining image coordinates associated with one or more user-selected, target individuals within an image frame of the multiple image frames, the image coordinates including user-device-generated image coordinates for the one or more user-selected, target individuals in the image frame, and being absent coordinates for one or more other non-user-selected individuals in the image frame;

executing facial recognition processing against individual faces within the image frame of the multiple image frames;

identifying the one or more target individuals in the image frame from the received image coordinates;

saving representative data of the one or more target individuals to a whitelist; and

producing a privacy protected version of at least one image frame of the multiple image frames, wherein the privacy protected version of the at least one image frame has one or more altered image features associated with the one or more other individuals within the at least one image frame.

9. The system of claim 8, wherein the obtaining image coordinates associated with the one or more target individuals within the image frame comprises receiving image coordinates derived from a user input through a touch screen of the user device, the user input having selected the one or more target individuals.

10. The system of claim 8, wherein the system further performs processing the at least one image frame with reference to the whitelist absent the identifying and the saving for the at least one image frame to identify the one or more target individuals within the at least one image frame.

11. The system of claim 8, wherein saving the representative data comprises clipping, at least, individual faces of the one or more target individuals within the image frame as facial images and saving the facial images to the whitelist.

12. The system of claim 8, wherein the one or more altered image features comprise blurred facial images of the one or more other individuals within the image frame.

13. The system of claim 8, wherein the system further distributes the privacy protected version of the at least one image frame with the one or more altered image features associated with the one or more other individuals within the at least one image frame.

14. A computer program product for facilitating privacy protection in a captured image, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code being executable by a processor to perform a method comprising;

obtaining multiple image frames captured via a user device;

obtaining image coordinates associated with one or more user-selected, target individuals within an image frame of the multiple image frames, the image coordinates including user-device-generated image coordinates for the one or more user-selected, target individuals in the image frame, and being absent coordinates for one or more other non-user-selected individuals in the image frame;

executing facial recognition processing against individual faces within the image frame of the multiple image frames;

identifying the one or more target individuals in the image frame from the received image coordinates;

saving representative data of the one or more target individuals to a whitelist; and

producing a privacy protected version of at least one image frame of the multiple image frames, wherein the privacy protected version of the at least one image frame has one or more altered image features associated with the one or more other individuals within the at least one image frame.

15. The computer program product of claim 14, wherein the obtaining image coordinates associated with the one or more target individuals within the image frame comprises receiving image coordinates derived from a user input through a touch screen of the user device, the user input having selected the one or more target individuals.

16. The computer program product of claim 14, wherein the method further comprises processing the at least one image frame with reference to the whitelist absent the identifying and the saving for the at least one image frame to identify the one or more target individuals within the at least one image frame.

17. The computer program product of claim 14, wherein saving the representative data comprises clipping, at least, individual faces of the one or more target individuals within the image frame as facial images and saving the facial images to the whitelist.