Method and system for customizing facial feature tracking using precise landmark finding on a neutral face image

• US 20020015512A1
• Filed: 07/24/2001
• Published: 02/07/2002
• Est. Priority Date: 11/06/1998
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Nevengineering Incorporated (Alphabet Inc.)
• Inventors: Buddenmeier, Ulrich F., Neven, Hartmut
• Granted Patent: US 6,714,661 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/20064 Wavelet transform [DWT]
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/262 using transform domain methods, e.g. Fourier domain methods
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships

Abstract

The present invention is embodied in a method and system for customizing a visual sensor for facial feature tracking using a neutral face image of an actor. The method may include generating a corrector graph to improve the sensor'"'"'s performance in tracking an actor'"'"'s facial features.

Claims

1. A method for customizing facial feature tracking, comprising:

capturing a front neutral face image of an actor;

automatically finding facial feature locations on the front neutral face image using elastic bunch graph matching;

automatically positioning nodes at the facial feature locations on the front neutral face image of the actor; and

manually correcting the positioning of the nodes on front neutral face image of the actor.

2. A method for customizing facial feature tracking as defined in claim 1, further comprising generating a corrector graph based on the corrected node positions.

3. A system for customizing facial feature tracking, comprising:

means for capturing a front neutral face image of an actor;

means for automatically finding facial feature locations on the front neutral face image using elastic bunch graph matching;

means for automatically positioning nodes at the facial feature locations on the front neutral face image of the actor; and

means for manually correcting the positioning of the nodes on front neutral face image of the actor.

4. A system for customizing facial feature tracking as defined in claim 3, further comprising means for generating a corrector graph based on the corrected node positions.

5. A method for customizing facial feature tracking, comprising:

capturing a front neutral face image of an actor;

automatically finding facial feature locations on the front neutral face image using image analysis based on wavelet component values generated from wavelet transformations of the front neutral face image;

automatically positioning nodes at the facial feature locations on the front neutral face image of the actor; and

manually correcting the positioning of the nodes on front neutral face image of the actor.

6. A method for customizing facial feature tracking as defined in claim 5, wherein the wavelet transformations use Gabor wavelets.

7. A method for customizing facial feature tracking, comprising:

capturing a front neutral face image of an actor;

finding facial feature locations on the front neutral face image using image analysis based on wavelet component values generated from wavelet transformations of the front neutral face image; and

generating a corrector graph for expressive facial features based on the wave component values at the facial feature locations on the front neutral face image.

8. A method for customizing facial feature tracking as defined in claim 7, wherein the wavelet transformations use Gabor wavelets.