Facial image processing methods and systems

• US 7,124,066 B2
• Filed: 04/30/2004
• Issued: 10/17/2006
• Est. Priority Date: 08/30/2000
• Status: Expired due to Term

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Kang, Sing Bing, Olynyk, Kirk, Guenter, Brian K., Raghupathy, Sashi, Marschner, Stephen
• Primary Examiner(s): JONES, HUGH M
• Application Number:
  US10/837,424
• Publication Number:
  US 20040204927A1
• Time in Patent Office: 900 Days
• Field of Search: 702/2, 382/118, 703/2
• US Class Current: 703/2
• 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 computer-implemented facial image-processing 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 further comprising after said measuring of the range map data, applying a generic face template to the range map data to reject noise that is associated with the range map data.

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

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

4. The method of claim 1 further comprising prior to deriving the 3-dimensional surface, filtering the range map data.

5. A facial image processing system comprising:

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;

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

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 system of claim 5, wherein the computerized image processor is configured to:

measure range map data;

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

compute surface normals to the 3-dimensional surfaec; and

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

7. The system of claim 6, wherein the computerized image processor is configured to filter the range map data prior to deriving the 3-dimensional surface.