# US 2008/0187246 A1 · Transforming a submitted image of a person based on a condition of the person

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2008/0187246 A1
- Document ID: US20080187246A1
- Status: Published application
- Kind: A1
- Application number: 11/671,751
- Filed: 2007-02-06
- Published: 2008-08-07
- Earliest claimed: 2007-02-06
- Assignees: Accenture Global Services Limited
- Inventors: Ana Cristina Andres Del Valle
- Web page: https://patentgrep.com/patent/US20080187246A1

## CPC

- G06T 3/18: Image warping, e.g. rearranging pixels individually
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## 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

### Claim 1

A method for processing a submitted image, comprising:
(a) receiving the submitted image of a person and associated data, the associated data being indicative of a condition of the person;
(b) obtaining, from a transformation model, a transformation parameter that is associated with a portion of the submitted image;
(c) applying the transformation parameter to the portion of the submitted image;
(d) rendering a transformed image from the transformation parameter;
(e) determining an error measure that gauges a discrepancy between the transformed image and actual data, the actual data being indicative of an actual image of the person when affected by the condition; and
(f) modifying a model parameter to reconfigure the transformation model.

### Claim 2 (depends on 1)

The method of claim 1, the transformation parameter comprising a deformation vector and (b) comprising:
(b)(i) forming a mesh that overlays the portion of the submitted image, the mesh having a plurality of vertices; and
(b)(ii) determining the deformation vector from the transformation model.

### Claim 3 (depends on 2)

The method of claim 2, (c) comprising:
(c)(i) applying the deformation vector to one of the plurality of vertices to obtain a transformed vertex.

### Claim 4 (depends on 3)

The method of claim 3, (d) comprising:
(d)(i) in response to (c)(i), rendering the transformed image from the mesh.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
(g) training the transformation model to reduce the error measure.

### Claim 6 (depends on 3)

The method of claim 3, (e) comprising:
(e)(i) measuring a distance between said one of the plurality of vertices and the transformed vertex.

### Claim 7 (depends on 6)

The method of claim 6, (e) further comprising:
(e)(ii) repeating (e)(i) for another vertex to obtain a plurality of differences: and
(e)(iii) determining a least square error from the plurality of differences.

### Claim 8 (depends on 7)

The method of claim 7, (f) comprising:
(f)(i) modifying the model parameter from the least square error.

### Claim 9 (depends on 1)

The method of claim 1, (b) comprising:
(b)(i) extracting global data from the associated data for the person;
(b)(ii) determining a cluster that is associated with the global data; and
(b)(iii) determining the transformation parameter from the cluster information and specific data for the person.

### Claim 10 (depends on 1)

The method of claim 1, wherein:
the transformation parameter comprises a texture alteration parameter;
(b) comprises determining the texture alteration parameter from the associated data for the person; and
(c) comprises applying the texture alteration parameter to the portion of the submitted image.

### Claim 11 (depends on 1)

The method of claim 1, wherein:
the transformation parameter comprises a hair descriptive parameter;
(b) comprises determining the hair descriptive parameter from the associated data for the person; and
(c) comprises applying the hair descriptive parameter to the portion of the submitted image.

### Claim 12 (depends on 1)

The method of claim 1, the portion of the submitted image comprising a face portion of the person.

### Claim 13 (depends on 1)

The method of claim 1, wherein:
the transformation parameter comprises a reshaping parameter;
(b) comprises determining the reshaping parameter from the associated data for the person; and
(c) comprises applying the reshaping parameter to the portion of the submitted image.

### Claim 14 (depends on 1)

The method of claim 1, the portion of the submitted image comprising a torso portion of the person.

### Claim 15

An apparatus for processing a submitted image of a person, comprising:
a search module matching an image model to a portion the submitted image to obtain modeled data for the submitted image;
a transformation control module receiving associated data for the person and determining a transformation parameter from a transformation model;
a image transformation module processing the modeled information, the submitted image, and the transformation parameter to render a transformed image; and
an error analysis module determining an error measure and modifying a model parameter to reconfigure the transformation model that is utilized by the transformation control module.

### Claim 16 (depends on 15)

The apparatus of claim 15, further comprising:
a training module configuring the transformation model to reduce the error measure.

### Claim 17 (depends on 15)

The apparatus of claim 15, wherein:
the transformation parameter comprising a deformation vector;
the search module forming a mesh that overlays the portion of the submitted image, the mesh having a plurality of vertices; and
the transformation control module determining the deformation vector from the transformation model.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein
the image transformation module applying the deformation vector to one of the plurality of vertices to obtain a transformed vertex.

### Claim 19 (depends on 15)

The apparatus of claim 15, further comprising:
a statistical analysis module associating the person to a cluster based on global data, the global data being determined from the associated data for the person; and
the transformation control module determining the transformation parameter by utilizing cluster information.

### Claim 20 (depends on 15)

The apparatus of claim 15, further comprising:
a data structure storing image model information and providing the image model information to the search module.

### Claim 21

A computer-readable medium having computer-executable instructions to perform the steps comprising:
(a) receiving the submitted image of a person and associated data, the associated data being indicative of a condition of the person;
(b) obtaining, from a transformation model, a transformation parameter that is associated with a portion of the submitted image;
(c) applying the transformation parameter to the submitted image;
(d) rendering a transformed image from the transformation parameter;
(e) determining an error measure that gauges a discrepancy between the transformed image and actual data, the actual data being indicative of an actual image of the person when affected by the condition; and
(f) modifying a model parameter to reconfigure the transformation model.

### Claim 22 (depends on 21)

The computer medium of claim 21, having computer-executable instructions to perform the steps comprising:
(b)(i) forming a mesh that overlays the portion of the submitted image, the mesh having a plurality of vertices; and
(b)(ii) determining a deformation vector from the transformation model, the transformation parameter comprising the deformation vector.

### Claim 23 (depends on 22)

The computer medium of claim 22, having computer-executable instructions to perform the steps comprising:
(c)(i) applying the deformation vector to one of the plurality of vertices to obtain a transformed vertex.

### Claim 24 (depends on 23)

The computer medium of claim 23, having computer-executable instructions to perform the steps comprising:
(d)(i) in response to (c)(i), rendering the transformed image from the mesh.

### Claim 25

A method for processing a submitted image, comprising:
(a) training a transformation model to reduce an error measure for transforming an image;
(b) receiving, from a requester, the submitted image of a person and associated data, the associated data being indicative of a condition of the person;
(c) obtaining, from a transformation model, a transformation parameter that is associated with a portion of the submitted image;
(d) applying the transformation parameter to the portion of the submitted image;
(e) obtaining a transformed image from the transformation parameter; and
(f) returning the transformed image to the requester.

### Claim 26 (depends on 1)

The method of claim 1, the transformation model including texture characteristics of the submitted image.

### Claim 27 (depends on 1)

The method of claim 1, the transformation model including pattern characteristics of the submitted image.

### Claim 28 (depends on 1)

The method of claim 1, the transformation model including color characteristics of the submitted image.

### Claim 29 (depends on 1)

The method of claim 1, the submitted image comprising a photographic image.

### Claim 30 (depends on 1)

The method of claim 1, the submitted image comprising medical imaging.

### Claim 31 (depends on 1)

The method of claim 1, further comprising:
(g) receiving feedback from a user to modify the model parameter; and
(h) repeating (g) until the error measure is not greater than a desired error amount.