Facial image processing methods and systems

• US 20060013449A1
• Filed: 09/01/2005
• Published: 01/19/2006
• Est. Priority Date: 08/30/2000
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Kang, Sing Bing, Olynyk, Kirk, Guenter, Brian K., Raghupathy, Sashi, Marschner, Stephen
• Granted Patent: US 7,152,024 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06T 15/506 Illumination models
• CPC Class Codes: G06T 7/521 from laser ranging, e.g. using interferometry; from the projection of structured light
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

In the described embodiment, methods and systems for processing facial image data for use in animation are described. In one embodiment, a system is provided that illuminates a face with illumination that is sufficient to enable the simultaneous capture of both structure data, e.g. a range or depth map, and reflectance properties, e.g. the diffuse reflectance of a subject'"'"'s face. This captured information can then be used for various facial animation operations, among which are included expression recognition and expression transformation.

Claims

1. A facial image-processing system comprising:

means for illuminating a face with multiple different light sources;

means for measuring range map data from said illuminating;

means for measuring image data from said illuminating;

means for deriving a 3-dimensional surface from the range map data;

means for computing surface normals to the 3-dimensional surface; and

means for processing the surface normals and the image data to derive an albedo map; and

means for applying a generic face template to the range map data to reject noise that is associated with the range map data.

2. The system of claim 1, wherein at least one of the light sources is polarized.

3. The system of claim 1, wherein all of the light sources are polarized.

4. The system of claim 1 further comprising means for filtering the range map data.

5. A facial image processing method comprising:

providing multiple different light sources, one of which providing structured light that can be projected onto the face of a subject, another of which providing light from which specularly-suppressed, diffuse reflectance data from the subject'"'"'s face can be ascertained;

providing a camera configured to capture structure and reflectance data from an illumination of the subject'"'"'s face with the multiple different light sources; and

providing a computerized image processor configured to process the structure and reflectance data to provide an albedo map that describes specular-suppressed diffuse reflectance properties of the subject'"'"'s face and dimensional data that describes dimensional aspects of the subject'"'"'s face, wherein the computerized image processor filters the range map data by applying a generic face template to the data.

6. The method of claim 5, wherein said providing a computerized image processor provides a computerized image processor that is configured to:

measure range map data;

compute a 3-dimensional surface from the range map data;

compute surface normals to the 3-dimensional surface; and

derive the albedo map from the surface normals and the reflectance data.

7. The method of claim 6, wherein said providing a computerized image processor provides a computerized image processor that is configured to filter the range map data prior to deriving the 3-dimensional surface.

8. A facial image-processing system comprising:

one or more processors;

one or more computer-readable media;

computer-readable instructions on the one or more computer-readable media which, when executed by the one or more processors, cause the one or more processors to execute a method comprising;

illuminating a face with multiple different light sources;

measuring range map data from said illuminating;

measuring image data from said illuminating;

deriving a 3-dimensional surface from the range map data;

computing surface normals to the 3-dimensional surface; and

processing the surface normals and the image data to derive an albedo map; and

applying a generic face template to the range map data to reject noise that is associated with the range map data.

9. The system of claim 8, wherein at least one of the light sources is polarized.

10. The system of claim 8, wherein all of the light sources are polarized.

11. The system of claim 8, wherein the method further comprises filtering the range map data.