US 5,850,463 A · Facial image processing method and facial image processing apparatus

Abstract

A method and apparatus are provided for merging plural facial images by continuously varying the shape interpolation ratio while preventing the positions of facial features from shifting, retaining a specific resemblance between the synthesized image and either of the source images in specific facial features, and changing the facial expression using a simple operation. The facial image processing apparatus comprises first shape matching processor 11 for grossly matching a facial image G1 with a background facial image G3 by focusing on the feature areas of facial image G1 and converting the coordinates of particular points in the feature areas in the shape model of this facial image G1 to the coordinates of the corresponding point in the shape model of the background facial image G3; a second shape matching processor 12 for grossly matching a facial image G2 with a background facial image G3 by focusing on the feature areas of facial image G2 and converting the coordinates of particular points in the feature areas in the shape model of this facial image G2 to the coordinates of the corresponding point in the shape model of the background facial image G3; shape interpolation processor 1 for interpolating the coordinates of corresponding points in the matched shape models of facial images G1 and G2 and the shape model of background facial image G3 at a specific interpolation ratio; and color interpolation processor 2 for interpolating the color of each pixel in the shape model interpolated by shape interpolation processor 1 using a specific interpolation ratio.

Claims18

Dependent claims

A facial image processing method for synthesizing a facial image from first and second source facial images and a background facial image, each of the three facial images comprising associated shape data and associated image data, the associated shape data representing an associated shape model and including a plurality of points with associated coordinates, the associated image data representing a color of each pixel in the associated shape model, the method comprising the steps of:

(a) grossly matching the first source facial image with the background facial image by converting coordinates of particular points in preselected feature areas in the shape model of the first source facial image to coordinates of corresponding points in the shape model of the background image so as to produce a first matched shape model;
(b) grossly matching the second source facial image with the background facial image by converting coordinates of particular points in preselected feature areas in the shape model of the second source facial image to coordinates of corresponding points in the shape model of the background facial image so as to produce a second matched shape model;
(c) interpolating the coordinates of the corresponding points in the matched shape models of the first and second source facial images and the shape model of the background facial image at a shape interpolation ratio so as to produce an interpolated shape model with associated shape interpolated data;
and
(d) interpolating a color of each pixel in the interpolated shape model at a color interpolation ratio, based on the shape data and the image data of the three images and the shape interpolated data so as to produce a synthesized image.

2 more elements

A image processing apparatus for synthesizing a facial image from first and second source facial images and a background facial image, each of the three facial images comprising associated shape data and associated image data, the associated shape data representing an associated shape model and including a plurality of points with associated coordinates, the associated image data representing a color of each pixel in the associated shape model, the apparatus comprising:

a first shape matching processor for grossly matching the first source facial image with the background facial image by converting coordinates of particular points in preselected feature areas in the shape model of the first source facial image to coordinates of corresponding points in the shape model of the background facial image so as to produce a first matched shape model;
a second shape matching processor for grossly matching the second source facial image with the background facial image by converting coordinates of particular points in preselected feature areas in the shape model of the second source facial image to coordinates of corresponding points in the shape model of the background facial image so as to produce a second matched shape model;
a shape interpolation processor which is coupled to said first and second shape matching processors for interpolating the coordinates of the corresponding points in the matched shape models of the first and second source facial images and the shape model of the background facial image at a shape interpolation ratio so as to produce an interpolated shape model with associated shape interpolated data;
and
a color interpolation processor which is coupled to said shape interpolation processor for interpolating a color of each pixel in the interpolated shape model at a color interpolation ratio, based on the shape data and the image data of the three facial images and the shape interpolated data so as to produce a synthesized image.

2 more elements

Dependencies are inferred from the claim text.

Facial image processing method and facial image processing apparatus

Life of this patent

Facial image processing method and facial image processing apparatus

Life of this patent

Abstract

Claims18