Transforming a submitted image of a person based on a condition of the person

• US 8,014,589 B2
• Filed: 08/05/2010
• Issued: 09/06/2011
• Est. Priority Date: 02/06/2007
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Andres Del Valle, Ana Cristina
• Primary Examiner(s): Kassa; Yosef
• Application Number:
  US12/851,076
• Publication Number:
  US 20110064331A1
• Time in Patent Office: 397 Days
• Field of Search: 382/274, 382/275, 382/278, 358/537, 358/538, 358/463
• US Class Current: 382/154
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually

Abstract

Apparatuses, computer media, and methods for altering a submitted image of a person. The submitted image is transformed in accordance with associated data regarding the person'"'"'s condition. Global data may be processed by a statistical process to obtain cluster information, and the transformation parameter is then determined from cluster information. The transformation parameter is then applied to a portion of the submitted image to render a transformed image. A transformation parameter may include a texture alteration parameter, a hair descriptive parameter, or a reshaping parameter. An error measure may be determined that gauges a discrepancy between a transformed image and an actual image. A transformation model is subsequently reconfigured with a modified model in order to reduce the error measure. Also, the transformation model may be trained to reduce an error measure for the transformed image.

Claims

1. A computer-implemented method comprising:

obtaining a before image of a person taken before a portion of the person'"'"'s body has changed, and an actual after image of the person taken after the portion of person'"'"'s body has changed;

applying model parameters to the before image of the person to generate a forecasted after image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed;

comparing the actual after image to the forecasted after image to determine an error between the actual after image and the forecasted after image; and

adjusting the model parameters based on the error.

2. The method of claim 1, wherein the portion of the person'"'"'s body comprises the person'"'"'s face or torso.

3. The method of claim 1, wherein the actual after image represents an image of the person taken after the portion of the person'"'"'s body has changed due to a health condition, and the forecasted after image represents an image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed due the health condition.

4. The method of claim 3, wherein the health condition comprises aging or weight change.

5. The method of claim 1, wherein the before image, the actual after image, and the forecasted after image comprises medical images.

6. The method of claim 1, wherein comparing the actual after image to the forecasted after image further comprises:

applying a set of points over the actual after image and the forecasted after image; and

comparing a position of one or more points of the set over the actual after image with a position of one or more corresponding points of the set over the forecasted after image.

7. The method of claim 6, wherein comparing a position of one or more points of the set over the actual after image with a position of one or more corresponding points of the set over the forecasted after image further comprises:

determining a square error for each corresponding point; and

assigning a weight to the square error for each corresponding point based on a relative importance of the point.

21. The method of claim 1, further comprising:

after adjusting the model parameters, receiving a before image of a different person; and

applying the adjusted model parameters to the before image of the different person to generate a forecasted after image of the different person.

8. A system comprising:

one or more computers; and

a computer-readable medium coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising;

obtaining a before image of a person taken before a portion of the person'"'"'s body has changed, and an actual after image of the person taken after the portion of person'"'"'s body has changed;

applying model parameters to the before image of the person to generate a forecasted after image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed;

comparing the actual after image to the forecasted after image to determine an error between the actual after image and the forecasted after image; and

adjusting the model parameters based on the error.

9. The system of claim 8, wherein the portion of the person'"'"'s body comprises the person'"'"'s face or torso.

10. The system of claim 8, wherein the actual after image represents an image of the person taken after the portion of the person'"'"'s body has changed due to a health condition, and the forecasted after image represents an image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed due the health condition.

11. The system of claim 10, wherein the health condition comprises aging or weight change.

12. The system of claim 8, wherein the before image, the actual after image, and the forecasted after image comprises medical images.

13. The system of claim 8, wherein comparing the actual after image to the forecasted after image further comprises:

applying a set of points over the actual after image and the forecasted after image; and

comparing a position of one or more points of the set over the actual after image with a position of one or more corresponding points of the set over the forecasted after image.

14. The system of claim 13, wherein comparing a position of one or more points of the set over the actual after image with a position of one or more corresponding points of the set over the forecasted after image further comprises:

determining a square error for each corresponding point; and

assigning a weight to the square error for each corresponding point based on a relative importance of the point.

15. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

obtaining a before image of a person taken before a portion of the person'"'"'s body has changed, and an actual after image of the person taken after the portion of person'"'"'s body has changed;

applying model parameters to the before image of the person to generate a forecasted after image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed;

comparing the actual after image to the forecasted after image to determine an error between the actual after image and the forecasted after image; and

adjusting the model parameters based on the error.

16. The computer storage medium of claim 15, wherein the portion of the person'"'"'s body comprises the person'"'"'s face or torso.

17. The computer storage medium of claim 15, wherein the actual after image represents an image of the person taken after the portion of the person'"'"'s body has changed due to a health condition, and the forecasted after image represents an image that predicts how the portion of the person'"'"'s body will appear after the portion of the person'"'"'s body has changed due the health condition.

18. The computer storage medium of claim 17, wherein the health condition comprises aging or weight change.

19. The computer storage medium of claim 15, wherein the before image, the actual after image, and the forecasted after image comprises medical images.

20. The computer storage medium of claim 15, wherein comparing the actual after image to the forecasted after image further comprises:

applying a set of points over the actual after image and the forecasted after image; and

comparing a position of one or more points of the set over the actual after image with a position of one or more corresponding points of the set over the forecasted after image.