Method and apparatus for automatic face blurring

• US 6,959,099 B2
• Filed: 12/06/2001
• Issued: 10/25/2005
• Est. Priority Date: 12/06/2001
• Status: Expired due to Fees

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Trajkovic, Miroslav, Gutta, Srinivas, Philomin, Vasanth, Colmenarez, Antonio J.
• Primary Examiner(s): Chang, Jon
• Application Number:
  US10/011,612
• Publication Number:
  US 20030108240A1
• Time in Patent Office: 1,419 Days
• Field of Search: 382/100, 382/118, 382/164, 382/181, 382/264, 382/282, 382/291, 704/231, 704/237, 704/239, 704/246, 704/251
• US Class Current: 382/100
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

An image processing system is disclosed that provides automatic face or skin blurring for images. All faces or skin can be blurred, or specific faces can be blurred. In one aspect of the invention, a particular face is blurred on an image or on a series of images in a video. Faces are determined in an image, and face matching is performed to match a particular face to faces in the image. If a match is found, the face or a portion of the face is blurred in the image. The blurring is performed on a portion of the image containing the particular face. Blurring may be performed through a variety of techniques. In another aspect of the invention, voice processing is used as an adjunct to or in place of face analysis to determine if a face in an image or series of images should be blurred. In another aspect of the invention, all faces or human skin in an image or series of images is blurred.

Claims

1. A method for automatically blurring faces, said method comprising the steps of:

storing voice information of at least one relevant person;

analyzing an image to determine at least one face in the image, the image being one image in a series of images from a video;

determining if sound in audio corresponding to the video can be assigned to a relevant person by comparing information in the sound with the stored voice information; and

blurring at least one region of the image containing at least a portion of the at least one face, said blurring step comprising blurring regions of each of the images when the audio corresponds to a relevant person, each of the regions comprising one of the at least one faces, such that all faces in the images are blurred.

2. The method as claimed in claim 1, wherein the method further comprises the step of:

storing face information identifying at least one relevant face,

wherein the at least one face comprises a plurality of faces,

wherein the step of analyzing further comprises the step of identifying at least one relevant face from the plurality of faces by comparing face information of said determined at least one face with said stored face information, and

wherein the step of blurring further comprises blurring a region of the image containing at least a portion of the at least one relevant face.

3. The method as claimed in claim 1, wherein:

the step of blurring further comprises the step of blurring a region of each of the images when the audio corresponds to a relevant person, each of the regions comprising a face that corresponds to the relevant person.

4. The method as claimed in claim 1, wherein a particular region comprises a face, and wherein the step of blurring further comprises blurring a portion of the region where the entire face is blurred.

5. The method as claimed in claim 1, wherein the step of analyzing further comprises the step of determining, for each face in the image, a location of the face.

6. The method as claimed in claim 5, wherein the step of determining a location further comprises the step of determining, for each location, an area.

7. The method as claimed in claim 6, wherein each area comprises a shape.

8. The method as claimed in claim 1, wherein:

the at least one face comprises a plurality of faces;

the step of analyzing further comprises the step of identifying regions in the image wherein the plurality of faces exist; and

the step of blurring further comprises blurring each of the regions so that each of the plurality of faces is blurred.

9. A system for automatically blurring faces, said system comprising:

an input for receiving an image in a series of images from a video;

a first memory for storing computer-readable code;

a second memory for storing voice information of at least one relevant person; and

a processor operatively coupled to said first and second memories, said processor configured to implement said computer-readable code, said computer-readable code causing said processor;

analyze said image to determine at least one specified human body feature in the image;

determine if sound in audio corresponding to the video can be assigned to a relevant person by comparing information in the sound with the stored voice information; and

blur at least one region of the image containing at least a portion of the at least one specified human body feature when the audio corresponds to a relevant person.

10. The system as claimed in claim 9, wherein the at least one specified human body feature comprises a portion of a face.

11. The system as claimed in claim 9, wherein the at least one specified human body feature comprises human skin.

12. An article of manufacture comprising:

a computer-readable medium having computer readable code means embodied thereon, said computer-readable program code means causing a processor to perform the steps of;

storing voice information of at least one relevant person;

analyzing an image to determine at least one face in the image, the image being one image in a series of images from a video;

determining if sound in audio corresponding to the video can be assigned to a relevant person by comparing information in the sound with the stored voice information; and

blurring at least one region of the image containing at least a portion of the at least one face, said blurring step comprising blurring regions of each of the images when the audio corresponds to a relevant person, each of the regions comprising one of the at least one faces, such that all faces in the images are blurred.