Face tracking
First Claim
Patent Images
1. A computer-implemented method comprising:
- using a processor to perform the steps of;
receiving a first digital image in a sequence of digital images and eye and mouth coordinates;
outputting eye and mouth coordinates on a subsequent digital image in the sequence of digital images; and
computing transformation parameters that represent a transformation from a base face model for the first digital image to a subsequent deformable model for the subsequent digital image;
wherein receiving comprises estimating the base face model, denoted Mb, and the base face model'"'"'s transformation parameters, denoted T′
, by the eye and mouth coordinates;
wherein outputting comprises;
calculating an initial model, denoted M, for the subsequent digital image as a transformed base model Mb using the transformation parameters T′
,rotating the subsequent image to the first digital image, denoted I(x,y), to generate a normalized model of the initial model M;
calculating a horizontal and vertical gradient map on the rotated image; and
estimating new transformation parameters, denoted T*, by minimizing an energy function E(T,I(x,y)) representative of the goodness of fit between the transformed model and the corresponding digital image, and of the optimality of the new transformation parameters, where T* corresponds to the complex argument of the minimum of the energy function, denoted arg min T E(T,I(x,y)).
1 Assignment
0 Petitions
Accused Products
Abstract
A medium bears a deformable model configured to enable a machine to estimate positions of four points defined by X and Y coordinates, each of the points representing a facial element position in a digital image.
19 Citations
3 Claims
-
1. A computer-implemented method comprising:
using a processor to perform the steps of; receiving a first digital image in a sequence of digital images and eye and mouth coordinates; outputting eye and mouth coordinates on a subsequent digital image in the sequence of digital images; and computing transformation parameters that represent a transformation from a base face model for the first digital image to a subsequent deformable model for the subsequent digital image; wherein receiving comprises estimating the base face model, denoted Mb, and the base face model'"'"'s transformation parameters, denoted T′
, by the eye and mouth coordinates;wherein outputting comprises; calculating an initial model, denoted M, for the subsequent digital image as a transformed base model Mb using the transformation parameters T′
,rotating the subsequent image to the first digital image, denoted I(x,y), to generate a normalized model of the initial model M; calculating a horizontal and vertical gradient map on the rotated image; and estimating new transformation parameters, denoted T*, by minimizing an energy function E(T,I(x,y)) representative of the goodness of fit between the transformed model and the corresponding digital image, and of the optimality of the new transformation parameters, where T* corresponds to the complex argument of the minimum of the energy function, denoted arg min T E(T,I(x,y)). - View Dependent Claims (2, 3)
Specification