Automatic face detection and identity masking in images, and applications thereof

• US 8,098,904 B2
• Filed: 03/31/2008
• Issued: 01/17/2012
• Est. Priority Date: 03/31/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ioffe, Sergey, Williams, Lance, Strelow, Dennis, Frome, Andrea, Vincent, Luc
• Primary Examiner(s): WERNER, BRIAN P
• Application Number:
  US12/078,464
• Publication Number:
  US 20090262987A1
• Time in Patent Office: 1,387 Days
• Field of Search: None
• US Class Current: 382/118
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

A method and system of identity masking to obscure identities corresponding to face regions in an image is disclosed. A face detector is applied to detect a set of possible face regions in the image. Then an identity masker is used to process the detected face regions by identity masking techniques in order to obscure identities corresponding to the regions. For example, a detected face region can be blurred as if it is in motion by a motion blur algorithm, such that the blurred region can not be recognized as the original identity. Or the detected face region can be replaced by a substitute facial image by a face replacement algorithm to obscure the corresponding identity.

Claims

1. A method for obscuring one or more identities in an image, comprising:

(1) detecting, in an image, a region corresponding to a face;

(2) selecting a portion of the region that includes one or more features of the face; and

(3) motion blurring the portion to obscure the one or more features of the face based at least in part upon an orientation of the face.

2. The method of claim 1, wherein (1) comprises:

checking the detected region with stored public images; and

rejecting the detected region wherein the detected region matches a stored public image.

3. The method of claim 1, wherein (2) comprises selecting at least one of a nose, an eye, a mouth, and an outline of the face.

4. The method of claim 1, wherein (3) comprises motion blurring the one or more features of the face based on a canonical map function.

5. The method of claim 1, wherein (3) comprises motion blurring the one or more features of the face using Line Integral Convolution.

6. The method of claim 1, wherein (3) comprises:

determining an orientation of the face; and

motion blurring the portion of the region based on the orientation of the face.

7. The method of claim 6, wherein determining the orientation of the face comprises:

associating a first vector with the face; and

determining a relationship between the first vector and a second vector associated with the image.

8. A system for obscuring an identity in an image, comprising:

a processing pipeline server configured to obscure the identity in the image, wherein the processing pipeline server comprises;

a face detector configured to detect a region in the image corresponding to a face; and

an identity masker configured to obscure the identity corresponding to the detected region by motion blurring, based at least in part upon an orientation of the face, a portion of the detected region that includes one or more features of the face.