Image Blending System, Method and Video Generation System

• US 20080043041A2
• Filed: 04/05/2007
• Published: 02/21/2008
• Est. Priority Date: 04/06/2006
• Status: Abandoned Application

• Current Assignee: Fremantlemedia
• Original Assignee: Fremantlemedia
• Inventors: Hedenstroem, Erik, Caulfield, Declan
• Application Number:
  US11/696,882
• Publication Number:
  US 20070236513A1
• Time in Patent Office: Days
• US Class Current: 345/634
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A method and system for image blending is disclosed. A destination image is received (100), the destination image including an image portion to be replaced and having characteristics associated with the identified image portion. A source image is also received (130). An image portion of the source image to be inserted into the destination image is identified (140). Where necessary, parameters of the image portion to be inserted are transformed to match those of the image portion to be replaced (150). The image portion to be inserted is then blended into the destination image in dependence on the image portion to be replaced and its associated characteristics (160). A video generation system using these features is also disclosed.

Claims

1. An image blending system arranged to receive a source image and a destination image, the destination image including an image portion to be replaced and having characteristics associated with the identified image portion, wherein the image blending system includes a processor arranged to:

identify an image portion of the source image to be inserted into the destination image;

where necessary, transform parameters of the image portion to be inserted to match those of the image portion to be replaced; and

,

blend the image portion to be inserted into the destination image in dependence on the image portion to be replaced and its associated characteristics.

2. An image blending method comprising:

(a) receiving a destination image, the destination image including an image portion to be replaced and having characteristics associated with the identified image portion;

(b) receiving a source image;

(c) identifying an image portion of the source image to be inserted into the destination image;

(d) where necessary, transforming parameters of the image portion to be inserted to match those of the image portion to be replaced; and

,

(e) blending the image portion to be inserted into the destination image in dependence on the image portion to be replaced and its associated characteristics.

3. A method according to claim 2, wherein step (a) further comprises:

(a1) identifying an image portion of the destination image to be replaced; and

,

(a2) extracting the characteristics associated from the image portion to be replaced from the destination image or an associated data source.

4. A method according to claim 3, further comprising:

performing steps (a1) and (a2) in advance;

recording data on the results of steps (a1) and (a2); and

,

performing step (e) in dependence on the recorded data.

5. A method according to claim 2, wherein the image portion to be replaced and the image portion to be inserted each include faces.

6. A method according to claim 2, wherein the parameters of the image portion to be replaced include at least selected ones of:

orientation of the subject of the image portion, colour space and size of the image portion.

7. A method according to claim 2, wherein the step (e) comprises the steps of:

(e1) computing an average colour matrix for each of the image portion to be inserted and for the image portion to be replaced;

(e2) computing a colour-offset matrix from the computed average colour matrices; and

,

(e3) applying the colour-offset matrix to the image portion to be inserted to thereby transfer chromatic parameters from the image portion to be replaced.

8. A method according to claim 7, further comprising:

prior to step (e2), blurring the average colour matrix of the image portion to be replaced.

9. A method according to claim 7, further comprising:

after step (e3), performing edge masking on the image portion to be inserted using an alpha mask.

10. A method according to claim 2, wherein the destination image comprises one of a plurality of images forming an image stream, the method further comprising:

repeating steps (d) and (e) in respect of each of the plurality of images.

11. A method according to claim 10, further comprising wherein the image portion to be replaced and the image portion to be inserted each include faces and the image stream also has an accompanying audio stream including dialogue, the method further comprising:

identifying a portion of the dialogue associated with the face of the image to be replaced for the respective image; and

,

manipulating the facial expressions of the face of the image to be inserted in dependence on the identified portion of audio dialogue.

12. A video generation system comprising:

a receiver arranged to receive a source image;

a processor arranged to;

identify an image portion of the source image to be inserted into a destination video data stream;

for each frame of the destination video data stream for which the image portion is to be inserted;

where necessary, transform parameters of the image portion to be inserted to match those of an image portion to be replaced in the respective frame;

blend the image portion to be inserted into the respective frame in dependence on the image portion to be replaced and its associated characteristics; and

,

output the blended video data stream.

13. A video generation system according to claim 12, further comprising:

a data store encoding the destination video data stream and being arranged to communicate with the processor.

14. A video generation system according to claim 13, wherein the encoded destination video data stream includes predetermined data on the associated characteristics of each frame for which an image portion can be inserted.

15. A video generation system according to claim 14, wherein the associated characteristics include at least selected ones of:

coordinate data for a predetermined feature in the image portion to be replaced;

chromatic parameters on the image portion to be replaced; and

audio data associated with the image portion to be replaced.

16. A video generation system according to claim 14, further comprising a processing system, the processor being arranged to receive a video data stream, to determine data on characteristics associated with at least selected frames of the video data stream and encode the data and video data stream in the data store.

17. A video generation system according to claim 16, further comprising a user interface arranged to receive an input from a user identifying said selected frames.

18. A video generation system according to claim 17, wherein the associated characteristics include at least selected ones of:

coordinate data for a predetermined feature in the image portion to be replaced;

chromatic parameters on the image portion to be replaced; and

audio data associated with the image portion to be replaced, the user interface being arranged to receive an input from a user identifying selected ones of the characteristics and being arranged to control said processor to determine data on the selected characteristics.