Apparatus for and method of synthesizing face image
View Patent ↗An image of a face of a person is acquired. Image data corresponding to the head is extracted from the image of the face. The image data is enlarged, reduced, or rotated to obtain an image of the head that is vibrating. The vibrating image of the head is displayed on a display.
1. A face image synthesis apparatus comprising:
an image input unit which fetches an image including a face of a person;
a face region acquisition unit which acquires a face region including a head of the person from the image; and
a face region processing unit which processes image data corresponding to the face region to form a face image that is vibrating in one of position, size, and rotation about an axis perpendicular to the face image.
2. The face image synthesis apparatus according to claim 1 , wherein the image input unit is a digital camera.
3. The image synthesis apparatus according to claim 1 , wherein
the image input unit fetches first and second different images of the face of the person, and
the face region acquisition unit acquires the face region including the head of the person from a differential image obtained from differences between the first and second images.
4. The face image synthesis apparatus according to claim 3 , wherein the face region acquisition unit defines the face region from the differential image by constructing vertical lines tangent to left and right profiles of the differential image, a first horizontal line passing through a vertical average of intersections of the first and second vertical lines with the differential image, and a second horizontal line tangent to an intersection of the left and right profiles.
5. The face image synthesis apparatus according to claim 1 , wherein
the image input unit fetches a single, first image including the face of the person, and
the face region acquisition unit generates a second image by shifting position of the first image and acquires the face region including the head of the person from a differential image produced from differences between the first and second images.
6. The face image synthesis apparatus according to claim 5 , wherein
the face region acquisition unit defines the face region from the differential image by constructing vertical lines tangent to left and right profiles of the differential image, a first horizontal line passing through a vertical average of intersections of the first and second vertical lines with the differential image, and a second horizontal line tangent to an intersection of the left and right profiles.
7. A face image synthesis method comprising:
fetching an image including a face of a person;
acquiring a face region including a head of the person from the image; and
processing image data corresponding to the face region and forming a face image that is vibrating in one of position, size, and rotation about an axis perpendicular to the face image.
8. The face image synthesis method according to claim 7 , wherein
fetching an image includes fetching first and second different images of the face of the person, and
acquiring a face region includes forming a differential image from the differences between the first and second images.
9. The face image synthesis method according to claim 8 , including defining a face region from the differential image by constructing vertical lines tangent to left and right profiles of the differential image, a first horizontal line passing through a vertical average of intersections of the first and second vertical lines with the differential image, and a second horizontal line tangent to an intersection of the left and right profiles.
10. The face image synthesis method according to claim 7 , wherein
fetching an image includes fetching a single, first image of the face of the person, and
acquiring a face region includes generating a second image by shifting position of the first image and acquiring the face region including the head of the person from a differential image produced from differences between the first and second images.
11. The face image synthesis method according to claim 10 , including defining a face region from the differential image by constructing vertical lines tangent to left and right profiles of the differential image, a first horizontal line passing through a vertical average of intersections of the first and second vertical lines with the differential image, and a second horizontal line tangent to an intersection of the left and right profiles.