Image processing method and apparatus

Patent metadata

Field	Value
Publication number	US-9811894-B2
Application number	US-201615155833-A
Country	US
Kind code	B2
Filing date	May 16, 2016
Priority date	Nov 14, 2013
Publication date	Nov 7, 2017
Grant date	Nov 7, 2017

Abstract

An image processing method is provided. The method includes obtaining a human facial image and providing a total of n number of source images in a preconfigured file, where n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file. The method also includes generating a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file, individually synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images, and combining the n number frames of synthesized images into a dynamic image in a time order.

First claim

What is claimed is:

1. An image processing method, comprising:
obtaining a human facial image;
providing a total of n number of source images in a preconfigured file, wherein n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file;
generating a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file;
individually synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images; and
combining the n number frames of synthesized images into a dynamic image in a time order.

2. The method according to claim 1 , wherein the obtaining of the human facial image further comprises:
obtaining a target image including the human facial image, aligning the target image with a preset mask, and extracting the human facial image from the target image based on the mask; or
capturing an image of a human face through a camera device with an interface displaying the mask to create the human facial image located within a human facial area of the mask, and extracting the human facial image from the captured image.

3. The method according to claim 2 , wherein the combining of the n number frames of synthesized images into the dynamic image based on the time order comprises:
quantifying true colors of each synthesized image of the n number frames of synthesized images into previously-specified 256 colors, setting a time delay for each synthesized image based on configuration parameters of the time delay contained in the preconfigured file, and combining the n number frames of synthesized images into the dynamic image based on the time delay of each synthesized image.

4. The method according to claim 1 , wherein the synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images further comprises:
zooming a t-th frame source image of the preconfigured file and the human facial image to a predetermined size, wherein t is a variable and the initial value oft is 1;
reading out the adjusting parameters of the t-th frame source image in the preconfigured file;
adjusting the human facial image based on the adjusting parameters of the t-th frame to obtain a t-th frame synthesized human facial image;
synthesizing the source image of the t-th frame and the t-th frame synthesized human facial image by an alpha merge to obtain a synthesized t-th frame image; and
incrementing a value oft by 1 and repeating from zooming the t-th frame source image of the preconfigured file and the human facial image to the predetermined size, until the value of t equals to the number n.

5. The method according to claim 4 , wherein:
the adjusting parameters comprise at least one of positional coordinates of the human facial image in the source image, a zooming ratio of the human facial image, a rotating angle and facial deformation parameters of the human facial image; and
wherein the adjusting of the human facial image based on the adjusting parameters further comprises:
adjusting the human facial image based on the adjusting parameters of the t-th frame to obtain a t-th frame synthesized human facial image by at least one of shifting position of the human facial image abased on the positional coordinates, zooming the human facial image based on the zooming ratio, rotating the human facial image based on the rotating angle, and changing facial features of the human facial image based on the deformation parameters.

6. The method according to claim 1 , wherein the combining of the n number frames of synthesized images into the dynamic image based on the time order comprises:
quantifying true colors of each synthesized image of the n number frames of synthesized images into previously-specified 256 colors, setting a time delay for each synthesized image based on configuration parameters of the time delay contained in the preconfigured file, and combining the n number frames of synthesized images into the dynamic image based on the time delay of each synthesized image.

7. The method according to claim 1 , wherein the source image comprises at least:
a foreground image and a background image.

8. An image processing apparatus, comprising:
an obtaining unit configured to obtain a human facial image;
a synthesizing unit configured to:
provide a total of n number of source images in a preconfigured file, wherein n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file;
generate a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file; and
individually synthesize the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images; and

a combining unit configured to combine the n number frames of synthesized images into a dynamic image in a time order.

9. The apparatus according to claim 8 , wherein the obtaining unit is further configured to:
obtain a target image including the human facial image, aligning the target image with a preset mask, and extracting the human facial image from the target image based on the mask; or
capture an image of a human face through a camera device with an interface displaying the mask to create the human facial image located within a human facial area of the mask, and extracting the human facial image from the captured image.

10. The apparatus according to claim 9 , wherein the synthesizing unit is further configured to:
zoom a t-th frame source image of the preconfigured file and the human facial image to a predetermined size, wherein t is a variable and the initial value oft is 1;
read out the adjusting parameters of the t-th frame source image in the preconfigured file are;
adjust the human facial image based on the adjusting parameters of the t-th frame to obtain a t-th frame synthesized human facial image;
synthesize the source image of the t-th frame and the t-th frame synthesized human facial image by an alpha merge to obtain a synthesized t-th frame image; and
increment a value oft by 1 and to repeat from zooming the t-th frame source image of the preconfigured file and the human facial image to the predetermined size, until the value of t equals to the number n.

11. The apparatus according to claim 9 , wherein:
the combining unit is further configured to quantify true colors of each synthesized image of the n number frames of synthesized images into previously-specified 256 colors, to set a time delay for each synthesized image based on configuration parameters of the time delay contained in the file, and to combine the n number frames of synthesized images into the dynamic image based on the time delay of each synthesized image.

12. The apparatus according to claim 8 , wherein the synthesizing unit is further configured to:
zoom a t-th frame source image of the preconfigured file and the human facial image to a predetermined size, wherein t is a variable and the initial value oft is 1;
read out the adjusting parameters of the t-th frame source image in the preconfigured file are;
adjust the human facial image based on the adjusting parameters of the t-th frame to obtain a t-th frame synthesized human facial image;
synthesize the source image of the t-th frame and the t-th frame synthesized human facial im

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Yu Xiaoguang
• Huang Shuguang
• Guo Xiaowei
• He Yang
• Zhang Chengzhao
• Huang Feiyue
• Yu Zongqiao

Classifications

• G06T2207/30201

  Face · CPC title

• G06T5/50 Primary

  using two or more images, e.g. averaging or subtraction · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• H04N5/265

  Mixing · CPC title

• G06T5/005

  Physics · mapped topic