Face Image Synthesis Method and Face Image Synthesis Apparatus
AssigneeNEC Corporation
InventorAtsushi Marugame
Life of this patent
Estimating the term…
Abstract
A face image synthesis apparatus includes a storage device (2) and an arithmetic processing unit (1). The storage device (2) stores a plurality of face images and a plurality of feature points including an origin. The plurality of feature points are set to each of the plurality of face images. The arithmetic processing unit (1) generates a plurality of deformed face images by deforming the plurality of face images so that the origin and the other feature points thereof are matched to each other and generates a synthesized face image from the deformed face images.
Claims25
A face image synthesis apparatus comprising:
- a storage device configured to store a plurality of face images and a plurality of feature points including an origin and being set to each of the plurality of face images;
- and
- an arithmetic processing unit configured to generate a plurality of deformed face images, origins thereof are located in a same position, and the plurality of feature points thereof are located in same positions, by deforming the plurality of face images, and to generate a synthesized face image from the plurality of deformed face images,
- wherein the plurality of feature points includes a basing point and a reference point, and
- the arithmetic processing unit includes:
- an image scaling section configured to generate a plurality of scaled face images by scaling the plurality of face images based on the plurality of face images and the plurality of feature points to a distance between preset feature points of each of the plurality of scaled face images being same;
- an image normalizing section configured to calculate a location of the reference point from the origin in each of the plurality of scaled face images based on the plurality of scaled face images and the plurality of feature points, to set a location of the reference point after face image synthesis, and to generate the plurality of deformed face images which are normalized to the reference point of each of the plurality of scaled face images being located in a position of the reference point after face image synthesis;
- and
- an image synthesizing section configured to generate the synthesized face image by matching the reference point of each of the plurality of deformed face images and calculating a weighted average of at least one of a color and a luminance by a synthesis ratio for each pixel based on the plurality of deformed face images and the plurality of feature points, and
- the plurality of feature points includes a first feature point located in first quadrant, a second feature point located in second quadrant, a third feature point located in third quadrant and a fourth feature point located in fourth quadrant from the origin.
(canceled)
(canceled)
A face image synthesis method comprising:
- (a) obtaining a plurality of face images and a plurality of feature points including an origin which are set to each of the plurality of face images;
- (b) generating a plurality of deformed face image by deforming the plurality of face images to include mutually at least two of the plurality of feature points located at same positions;
- and
- (c) generating a synthesized face image based on the plurality of deformed face images,
- wherein the plurality of feature points includes a basing point and a reference point, and
- a first feature point located in first quadrant, a second feature point located in second quadrant, a third feature point located in third quadrant and a fourth feature point located in fourth quadrant from the origin are included in the plurality of feature points, and
- said (b) generating includes:
- (b1) generating a plurality of scaled face images by scaling the plurality of face images based on the plurality of face images and the plurality of feature points to a distance between preset feature points of each of the plurality of scaled face images being same;
- (b2) calculating a location of the reference point from the origin in each of the plurality of scaled face images based on the plurality of scaled face images and the plurality of feature points, setting a location of the reference point after face image synthesis, and generating the plurality of deformed face images which are normalized to the reference point of each of the plurality of scaled face images being located in a position of the reference point after face image synthesis;
- and
- (c) generating includes:
- (c1) generating the synthesized face image by matching the reference point of each of the plurality of deformed face images and calculating a weighted average of at least one of a color and a luminance by a synthesis ratio for each pixel based on the plurality of deformed face images and the plurality of feature points.
(canceled)
(canceled)
A face image synthesis apparatus comprising:
- an image scaling unit configured to generate a plurality of deformed face images by deforming each of a plurality of face images on which a plurality of feature points and a reference point are set so that the plurality of feature points are located at same positions for the plurality of deformed face images;
- and
- a synthesized image generating unit configured to generate a synthesized face image by deforming the plurality of deformed face images to the reference points thereof having same location, and synthesizing at least one of color and luminance,
- wherein the plurality of feature points includes a first feature point located in first quadrant, a second feature point located in second quadrant, a third feature point located in third quadrant and a fourth feature point located in fourth quadrant from the origin.
A face image synthesis apparatus for synthesizing at least two face images or face-like images as input images to generate an other image, comprising:
- an image scaling means for conforming scales of the input images by using coordinates of five points corresponding to a right eye, a left eye, a nose and two positions on a mouth of the input images;
- an image normalizing means for generating normalized images by scaling each of the input images to the five points being located at predetermined positions;
- and
- an image synthesis means for generating said other image by synthesizing the normalized images.
A face image synthesis method comprising:
- (d) generating a plurality of deformed face images by deforming each of a plurality of face images on which a plurality of feature points and a reference point are set so that the plurality of feature points are located at same positions for the plurality of deformed face images;
- and
- (e) generating a synthesized face image by deforming the plurality of deformed face images to the reference points thereof having same location, and synthesizing at least one of color and luminance,
- wherein the plurality of feature points includes a first feature point located in first quadrant, a second feature point located in second quadrant, a third feature point located in third quadrant and a fourth feature point located in fourth quadrant from the origin.
A face image synthesis method for synthesizing at least two face images or face-like images as input images to generate an other image, comprising:
- conforming scales of the input images by using coordinates of five points corresponding to a right eye, a left eye, a nose and two positions on a mouth of the input images;
- generating normalized images by scaling each of the input images to the five points being located at predetermined positions;
- and
- generating said other image by synthesizing the normalized images.
(canceled)
Dependencies are inferred from the claim text.