CARTOON PERSONALIZATION

• US 20090252435A1
• Filed: 08/28/2008
• Published: 10/08/2009
• Est. Priority Date: 04/04/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Tang, Xiao-Ou, Wen, Fang, Xu, Ying-Qing
• Granted Patent: US 8,831,379 B2
• Time in Patent Office: Days
• US Class Current: 382/284
• CPC Class Codes: G06F 18/2148 characterised by the process organisation or structure, e.g. boosting cascade
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: G06V 10/7747 Organisation of the process, e.g. bagging or boosting
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

Embodiments that provide cartoon personalization are disclosed. In accordance with one embodiment, cartoon personalization includes selecting a face image having a pose orientation that substantially matches an original pose orientation of a character in a cartoon image. The method also includes replacing a face of the character in the cartoon image with the face image. The method further includes blending the face image with a remainder of the character in the cartoon image.

Claims

1. A system, comprising:

a face pose engine to determine pose orientation for a face image, the determined pose orientation being similar to an original pose orientation of a character in a cartoon image;

a geometry engine to replace a face of the character in the cartoon image with the face image; and

a face blender engine to blend the face image with a remainder of the character in the cartoon image.

2. The system of claim 1, further comprising:

a face filter engine to determine a suitability of the face image for integration into the cartoon image, wherein the suitability is based on whether the face image is within at least one of an acceptable illumination range or greater than a minimal resolution threshold,

wherein the geometry engine is to further replace a face of the character in the cartoon image with the face image if the face image is suitable for integration into the cartoon image.

3. The system of claim 1, further comprising:

a face detection engine to detect the face image from a photographic image; and

a face alignment engine to obtain landmarks from the detected face image for determining orientation of the detected face image.

4. The system of claim 1, further comprising:

a face tagging engine to group the face image with another similar face image using at least one of offline pre-processing or online clustering.

5. The system of claim 1, wherein the face tagging engine is to further enable a user to label the face image.

6. The system of claim 1, wherein the face tagging engine is to further rank a plurality of face images for similarity according to a user input using at least one of a linear discriminate analysis, a support vector machine (SVM) analysis, or a simple nearest-neighbor analysis.

7. The system of claim 1, wherein the geometry engine is to replace a face of the character with the face image by:

determine a portion of the character to be replaced with face image using an affine transform, the portion including the face of the character;

transform the face image to replace the portion of the character via warping using the affine transform; and

substitute the portion of the character with the transformed face image.

8. The system of claim 1, wherein the blending engine is to blend the face image with a remainder of the character in the cartoon image by performing at least one of a shade blending using illumination information of the character, illumination blending using Poisson Blending, or a color adjustment of the face image based on a skin color of the character.

9. The system of claim 1, further comprising a face detection engine to detect the face image from a photographic image by one of an integral imaging technique and a multi-view technique.

10. The system of claim 1, further comprising a face alignment engine to obtain landmarks from the detected face image by using a Bayesian Tangent Shape Model (BTSM) on the face image.

11. The system of claim 1, further comprising a user interface module to enable a user to select the face image from a plurality of face images based on at least one of pose orientation of the face image, size of the face image, or brightness of the face image.

12. A method, comprising:

selecting a face image having a pose orientation that substantially matches an original pose orientation of a character in a cartoon image;

replacing a face of the character in the cartoon image with the face image; and

blending the face image with a remainder of the character in the cartoon image.

13. The method of claim 12, further comprising:

determining a suitability of the face image for integration into the cartoon image, wherein the suitability is based on whether the face image is within at least one of an acceptable illumination range or greater than a minimal resolution threshold,

wherein the replacing a face of the character in the cartoon image with the face image includes replacing the face of the character if the face image is suitable for integration into the cartoon image.

14. The method of claim 12, further comprising:

detecting one or more face images from at least one photographic image by one of an integral imaging technique and a multi-view technique; and

obtaining landmarks of each detected face image for determining orientation of each face image by using a Bayesian Tangent Shape Model (BTSM) on each face image.

15. The method of claim 12, further comprising grouping the face image with another similar face image using at least one of offline pre-processing or online clustering.

16. The method of claim 12, wherein the replacing includes:

determining a portion of the character to be replaced with face image using an affine transform, the portion including the face of the character;

transforming the face image to replace the portion of the character via warping using the affine transform; and

substituting the portion of the character with the transformed face image.

17. The method of claim 12, wherein the blending further includes blending using illumination information of the character, illumination blending using Poisson Blending, and adjusting coloring the face image based on a skin color of the character.

18. The method of claim 12, further comprising selecting the face image from a plurality of face images based on at least one of pose orientation of the face image, size of the face image, or brightness of the face image.

19. A computer readable medium storing computer-executable instructions that, when executed, cause one or more processors to perform acts comprising:

selecting a face image having a pose orientation that substantially matches an original pose orientation of a character in a cartoon image;

determining a suitability of the face image for integration into the cartoon image, wherein the suitability is based on whether the face image is within at least one of an acceptable illumination range or greater than a minimal resolution threshold,

replacing a face of the character in the cartoon image with the face image if the face image is suitable for integration into the cartoon image; and

blending the face image with a remainder of the character in the cartoon image.

20. The computer readable medium of claim 19, wherein the replacing includes:

determining a portion of the character to be replaced with face image using an affine transform, the portion including the face of the character;

transforming the face image to replace the portion of the character via warping using the affine transform; and

substituting the portion of the character with the transformed face image, and

wherein the blending further includes blending using illumination information of the character, illumination blending using Poisson Blending, and adjusting coloring the face image based on a skin color of the character.