IP Library › Granted Patent US 8,698,796
Granted Patent B2
US 8,698,796 · App. 12/891,124 · Granted Apr 15, 2014

Image processing apparatus, image processing method, and program

Inventor: Daisuke Mochizuki (Chiba, JP)
Assignee: Sony Corporation
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,698,796
App. No.
12/891,124
Granted
Apr 15, 2014
Kind
B2
Abstract

In an image processing apparatus, a feature point acquirer acquires feature points, which are characteristic points on a face in an image presenting a face. A supplementary feature point calculator calculates supplementary feature points on the basis of the feature points acquired by the feature point acquirer. An image transform unit utilizes the feature points and the supplementary feature points to transform the image so as to match the structure of a face in a projected image that depicts the surface of a given three-dimensional face shape projected onto a flat plane.

Claims (27)

1. An image processing apparatus, comprising:

a processing circuit configured to

acquire feature points, which are characteristic points on a face in an image;

calculate distinct supplementary feature points in the image based on a combination of the acquired feature points; and

utilize the feature points and the distinct supplementary feature points to transform the image to match a reference face in a projected image, wherein the projected image is a representation of a three-dimensional face shape of the reference face that has been projected onto a flat plane, wherein the feature points are acquired in the form of at least both ends of the eyes in the image, and the distinct supplementary points are calculated in the form of points at positions separated from the outward ends of the eyes in the image by a predetermined distance and extending toward the outline of the face, and points at positions separated from both ends of the eyes by a predetermined distance and extending toward the mouth.

2. The image processing apparatus according to claim 1 , wherein the feature points are acquired in the form of at least both ends of the mouth in the image, and

the distinct supplementary feature points are calculated in the form of points at positions separated from both ends of the mouth in the image by a predetermined distance and extending toward the eyes,

points at positions separated from both ends of the mouth in the image by a predetermined distance and extending away from the eyes, and

points at positions separated from one end of the mouth in the image by a predetermined distance and extending toward the other end.

3. The image processing apparatus according to claim 1 , wherein the feature points are acquired in the form of at least the outline of the face in the image, and the processing circuit is further configured to

use the feature points as a basis for generating a texture image and substitute a skin color in the area extending outward from the outline of the face in the transformed image.

4. The image processing apparatus according to claim 3 , wherein the processing circuit is further configured to

extract a skin color of the face presented in the image from one or more predetermined regions defined by any of the feature points or the distinct supplementary feature points, wherein the substituted area extends outward from the outline of the face.

5. The image processing apparatus according to claim 3 , wherein the processing circuit is further configured to

generate a face model wherein the texture image has been applied to a reference face shape, wherein the face model generating means applies to the reference face shape a new texture image, which is obtained by compositing the texture image with a given image.

6. An image processing method, comprising:

acquiring feature points which are characteristic points on a face in an image;

calculating distinct supplementary feature points in the image based on a combination of the acquired feature points; and

utilizing the acquired feature points and the calculated distinct supplementary feature points to transform the image to match a reference face in a projected image, wherein the projected image is a representation of a three-dimensional face shape of the reference face that has been projected onto a flat plane, wherein the feature points are acquired in the form of at least both ends of the eyes in the image, and the distinct supplementary points are calculated in the form of points at positions separated from the outward ends of the eyes in the image by a predetermined distance and extending toward the outline of the face, and points at positions separated from both ends of the eyes by a predetermined distance and extending toward the mouth.

7. A non-transitory computer readable medium having stored thereon a program that when executed by a computer causes the computer to execute an image processing method comprising:

acquiring feature points which are characteristic points on a face in an image;

calculating distinct supplementary feature points in the image based on a combination of the acquired feature points; and

utilizing the acquired feature points and the calculated distinct supplementary feature points to transform the image to match a reference face in a projected image, wherein the projected image is a representation of a three-dimensional face shape of the reference face that has been projected onto a flat plane, wherein the feature points are acquired in the form of at least both ends of the eyes in the image, and the distinct supplementary points are calculated in the form of points at positions separated from the outward ends of the eyes in the image by a predetermined distance and extending toward the outline of the face, and points at positions separated from both ends of the eyes by a predetermined distance and extending toward the mouth.

8. An image processing apparatus, comprising:

feature point acquiring means for acquiring feature points, which are characteristic points on a face in an image;

distinct supplementary feature point calculating means for calculating distinct supplementary feature points in the image based on a combination of the feature points acquired by the feature point acquiring means; and

transform means for utilizing the feature points and the distinct supplementary feature points to transform the image to match a reference face in a projected image, wherein the projected image is a representation of a three-dimensional face shape of the reference face that has been projected onto a flat plane, wherein the feature points are acquired in the form of at least both ends of the eyes in the image, and the distinct supplementary points are calculated in the form of points at positions separated from the outward ends of the eyes in the image by a predetermined distance and extending toward the outline of the face, and points at positions separated from both ends of the eyes by a predetermined distance and extending toward the mouth.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 27, 2010
From: MOCHIZUKI, DAISUKE
To: SONY CORPORATION
Reel/Frame 025046/0652 →
Priority Claims (1)
JP 2009-260850 · Nov 16, 2009 · national
Continuity (1)
Related Publication 20110115786A1 · May 19, 2011