US7415152B2 — Method and system for constructing a 3D represent…

Claim 1

Independent Claim 256 words

A method in a computer system for generating a 3D image of an object, the method comprising: providing a 3D model of an object, the 3D model including a 3D image of a standard object and parameters indicating variations of an individual object; receiving a 2D image of the object; locating feature points of the 2D image of the object; calculating parameters that map the located feature points of the 2D image to feature points of a 2D representation of the 3D image of the standard object; computing 3D feature points of the 3D image of the object using the provided 3D model and the calculated parameters; after computing the 3D feature points, interpolating 3D non-feature points of the 3D image from the computed 3D feature points; and after the 3D non-feature points of the 3D image is interpolated, texture mapping the 2D image of the object to the 3D image with the computed 3D feature points and interpolated 3D non-feature points wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard object, P ∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}=(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 2

Independent Claim 256 words

A method in a computer system for generating a 3D image of an object, the method comprising: providing a 3D model of an object, the 3D model including a 3D image of a standard object and parameters indicating variations of an individual object; receiving a 2D image of the object; locating feature points of the 2D image of the object; calculating parameters that map the located feature points of the 2D image to feature points of a 2D representation of the 3D image of the standard object; computing 3D feature points of the 3D image of the object using the provided 3D model and the calculated parameters; after computing the 3D feature points, interpolating 3D non-feature points of the 3D image from the computed 3D feature points; and after the 3D non-feature points of the 3D image is interpolated, texture mapping the 2D image of the object to the 3D image with the computed 3D feature points and interpolated 3D non-feature points wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard object, P ∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}=(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 3

Dependent Claim 17 words

The method of claim 1 including aligning the 2D image of the object with the feature points.

Claim 4

Dependent Claim 22 words

The method of claim 1 including interpolating non-feature points of the 3D image of the object based on the set feature points.

Claim 5

Dependent Claim 21 words

The method of claim 1 including interpolating the texture map in an area occluded by the 3D image of the object.

Claim 6

Dependent Claim 35 words

The method of claim 1 wherein the feature points in the 2D representation of the 3D image of the standard object are two of the three coordinates of the 3D image of the standard object.

Claim 7

Dependent Claim 28 words

The method of claim 1 including generating the 3D image of the standard object by normalizing 3D images of objects and taking the average of the 3D images.

Claim 8

Dependent Claim 34 words

The method of claim 6 wherein the 3D model includes a 3D image of a standard object and an eigenvector matrix of the 3D image of the standard object adjusted by a parameter vector.

Claim 9

Dependent Claim 51 words

The method of claim 1 including: receiving a 2D image of a target object; generating 3D images of the object at different image conditions; and comparing the 2D image of the target object with 2D images derived from the generated 3D images to determine whether the target object matches the object.

Claim 10

Dependent Claim 311 words

A computer-readable medium containing instructions for controlling a computer system to generate a 3D image of a face, by a method comprising: providing a 3D model for a face, the 3D model combining 3D points of a standard face and parameters, the parameters representing variations of an individual face from the average face; receiving a 2D image of a face; locating feature points of the 2D image of the face; calculating parameters that map the located feature points of the 2D image to a 2D representation of the 3D points of the standard face; and computing points of the 3D image of the face based on the provided model using the calculated parameters; and after computing the points of the 3D image, texture mapping the 2D image of the face to the computed points of the 3D image of the face wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard object, P ∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}=(α 1 , α 2 , . . ., α m ) T ∈ 3n×m are the parameters. where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard face, P∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}+(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 11

Dependent Claim 311 words

A computer-readable medium containing instructions for controlling a computer system to generate a 3D image of a face, by a method comprising: providing a 3D model for a face, the 3D model combining 3D points of a standard face and parameters, the parameters representing variations of an individual face from the average face; receiving a 2D image of a face; locating feature points of the 2D image of the face; calculating parameters that map the located feature points of the 2D image to a 2D representation of the 3D points of the standard face; and computing points of the 3D image of the face based on the provided model using the calculated parameters; and after computing the points of the 3D image, texture mapping the 2D image of the face to the computed points of the 3D image of the face wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard object, P ∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}=(α 1 , α 2 , . . ., α m ) T ∈ 3n×m are the parameters. where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n , Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n points, S represents the standard face, P∈ 3n×m is the matrix of the first m eigenvectors of S , and {right arrow over (α)}+(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 12

Dependent Claim 22 words

The computer-readable medium of claim 9 , wherein the 3D model uses a subset of the n points that represents feature points.

Claim 13

Dependent Claim 29 words

The computer-readable medium of claim 9 including interpolating non-feature points of the 3D image of the face based on feature points set based on the provided model and parameters.

Claim 14

Dependent Claim 23 words

The computer-readable medium of claim 9 , including interpolating the texture map in an area occluded by the 3D image of the face.

Claim 15

Dependent Claim 52 words

The computer-readable medium of claim 9 including: receiving a 2D image of a target face; generating 3D images of the face at different image conditions; and comparing the 2D image of the target face with 2D images derived from the generated 3D images to determine whether the target face matches the face.

Claim 16

Dependent Claim 234 words

A computer-readable medium containing instructions for controlling a computer system to generate a 3D image of a face, comprising: a 3D model for a face, the 3D model combining 3D points of a standard face and parameters, the parameters representing variations of an individual face from the standard face; a 2D image of a face; a component that calculates parameters that map points of the 2D image to 2D points derived from the 3D points of the standard face; a component that computes points of the 3D image of the face based on the provided model using the calculated parameters; a component that texture maps the 2D image of the face onto the 3D image of the face; and a component that generates 2D images of the face from a texture mapped 3D image of the face at varying image conditions wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} points, S represents the standard face, P ∈ 3n×m is the matrix of the first m eigenvectors of S , where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n ,Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n and {right arrow over (α)}=(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 17

Dependent Claim 234 words

A computer-readable medium containing instructions for controlling a computer system to generate a 3D image of a face, comprising: a 3D model for a face, the 3D model combining 3D points of a standard face and parameters, the parameters representing variations of an individual face from the standard face; a 2D image of a face; a component that calculates parameters that map points of the 2D image to 2D points derived from the 3D points of the standard face; a component that computes points of the 3D image of the face based on the provided model using the calculated parameters; a component that texture maps the 2D image of the face onto the 3D image of the face; and a component that generates 2D images of the face from a texture mapped 3D image of the face at varying image conditions wherein the 3D model is represented by the following equation: S′= S +P{right arrow over (α)} points, S represents the standard face, P ∈ 3n×m is the matrix of the first m eigenvectors of S , where S=(X 1 , Y 1 , Z 1 , X 2 , . . . Y n ,Z n ) T ∈ 3n , X, Y, and Z are coordinates of the n and {right arrow over (α)}=(α 1 , α 2 , . . . , α m ) T ∈ m are the parameters.

Claim 18

Dependent Claim 18 words

The computer-readable medium of claim 14 wherein an image condition is a pose, an illumination, or an expression.

Claim 19

Dependent Claim 25 words

The computer-readable medium of claim 14 including a component that interpolates non-feature points of the 3D image of the face based on set feature points.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2011-08-19	2012-02-18	2012-08-19	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2015-08-19	2016-02-18	2016-08-19	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2019-08-19	2020-02-18	2020-08-19	$7700.00	Window Closed / Lapsed

Method and system for constructing a 3D representation of a face from a 2D representation

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag