# US 7,609,860 B2 · Bilinear illumination model for robust face recognition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 7,609,860 B2
- Document ID: US7609860B2
- Status: Granted
- Kind: B2
- Application number: 11/251,222
- Filed: 2005-10-14
- Published: 2006-12-14
- Granted: 2009-10-27
- Earliest claimed: 2005-06-14
- Assignees: Mitsubishi Electric Research Laboratories, Inc.
- Inventors: Jinho Lee; Baback Moghaddam; Hanspeter Pfister; Raghu Machiraju
- Web page: https://patentgrep.com/patent/US7609860B2

## CPC

- G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method recognizes a face in an image. A morphable model having shape and pose parameters is fitted to a face in an image to construct a three-dimensional model of the face. Texture is extracted from the face in the image using the three-dimensional model. The shape and texture are projected into a bilinear illumination model to generate illumination bases for the face in the image. The illumination bases for the face in the image are compared to illumination bases of each of a plurality of bilinear illumination models of known faces to identify the face in the image.

## Claims

### Claim 1

A method for recognizing an unknown face in an image, comprising a processor for performing steps of the method, comprising the steps of:
fitting a morphable model having shape and pose parameters to an unknown face in an image to construct a three-dimensional model of the face;
extracting texture from the unknown face in the image using the three-dimensional model;
projecting the shape and texture into a bilinear illumination model to generate illumination bases for the unknown face in the image; and
comparing the illumination bases for the unknown face in the image to illumination bases of each of a plurality of bilinear illumination models of known faces to identify the unknown face in the image.

### Claim 2 (depends on 1)

The method of claim 1, in which the fitting, extracting, projecting, and comparing steps are performed on a plurality of images of the unknown face.

### Claim 3 (depends on 2)

The method of claim 2, in which the plurality of images are acquired with varying poses of the unknown face, varying exposure, varying viewpoints, and varying directional illumination.

### Claim 4 (depends on 2)

The method of claim 2, in which the plurality of images are high-dynamic range images.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
scanning the unknown face to obtain a polygon mesh corresponding to a shape of the unknown face.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
converting the polygon mesh to an unstructured list of point samples.

### Claim 7 (depends on 1)

The method of claim 1, in which the bases are obtained by a singular value decomposition.