Method and apparatus for generating models of individuals

• US 7,006,102 B2
• Filed: 04/29/2003
• Issued: 02/28/2006
• Est. Priority Date: 04/30/2002
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Rowe, Simon Michael
• Primary Examiner(s): Bella, Matthew C.
• Assistant Examiner(s): Sajous, Wesner
• Application Number:
  US10/424,724
• Publication Number:
  US 20030201996A1
• Time in Patent Office: 1,036 Days
• Field of Search: 345/418, 345581-583, 382117-118, 351/208, 351/200, 351/204, 348/78
• US Class Current: 345/582
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 15/04 Texture mapping
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2219/2016 Rotation, translation, scaling
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: H04M 1/576 associated with a pictorial or graphical representation
• CPC Class Codes: H04M 1/72427 for supporting games or graphical animations
• CPC Class Codes: H04N 2007/145 Handheld terminals

Abstract

A communications system is described in which a plurality of mobile phones are provided, each including means for generating a user interface for enabling users to identify points in images as feature points. All of the phones are then operable to utilise points identified by users to generate 3D models of individuals in the images. The 3D models are generated by associating stored average depth data for points corresponding to the co-ordinates of the feature points and further points whose position is identified relative to the co-ordinates of the feature points. The 3D models are then used to generate images which are displayed on the mobile phones.

Claims

1. A method of generating texture render data comprising:

receiving an image, the image including a representation of an eye having a corner and a pupil;

identifying, in the received image, a portion of the image extending between the pupil and the corner of the eye represented in the image; and

utilizing the identified portion of the received image to generate texture render data, wherein the generation of texture render data comprises

copying at least some of the identified portion of the received image as texture render data, and

calculating the remainder of the texture render data utilizing the copied data, such that texture render data at a specified distance from the center of the pupil in the texture render data corresponds to image data from within the identified portion of the received image at a corresponding distance from the center of the pupil in the identified portion of the received image.

2. A method in accordance with claim 1, wherein the image includes a representation of a first and a second eye, each of the first and second eyes having a corner and a pupil, the method further comprising:

determining which eye, of the first and the second eyes, has a greater distance between the pupil and the corner of the eye; and

utilizing the identified portion of the received image extending between the pupil and the corner of the eye having the greater distance between the pupil and the corner, to generate texture render data.

3. A computer-readable data carrier storing computer executable process steps for causing a programmable computer to perform a method in accordance with claim 1.

4. A data carrier in accordance with claim 3, comprising a computer disc.

5. A data carrier in accordance with claim 4, wherein said computer disc comprises an optical, magneto-optical or magnetic disc.

6. A data carrier in accordance with claim 3, comprising an electric signal transferred via the Internet.

7. A method of generating a texture rendered model, the method comprising:

obtaining an image of an individual to be modeled, the image including a representation of an eye having a corner and a pupil;

identifying in the obtained image, a portion of the image extending between the pupil and the corner of the eye represented in the image;

utilizing the identified portion of the received image to generate texture render data, wherein texture render data at a specified distance from the center of the pupil is determined by utilizing image data from within the identified portion of the received image at the specified distance from the center of the pupil;

utilizing the obtained image data to generate a 3D computer wire mesh model; and

texture rendering the portions of the wire mesh model representing the eyes of the wire mesh model by utilizing the generated texture render data.

8. A method in accordance with claim 7, wherein animation of the eyes of the wire mesh model is achieved by re-rendering the portions of the wire mesh model representing the eyes by utilizing different portions of the generated texture render data.

9. An apparatus for generating texture render data comprising:

a receiver operable to receive an image including a representation of an eye having a corner and a pupil;

an identification unit operable to identify a portion of the image received by said receiver extending between the pupil and the corner of the eye represented in the image;

a copying unit operable to generate texture render data by copying at least some of the identified portion of the received image; and

a calculation unit operable to calculate the remainder of the texture render data utilizing the copied data, such that texture render data at a specified distance from the center of the pupil in the texture render data corresponds to image data from within the identified portion of the received image at a corresponding distance from the center of the pupil in the identified portion of the received image.

10. An apparatus in accordance with claim 9, wherein

the identification unit is operable to;

process a received image including a representation of a first eye and a second eye, each having a corner and a pupil, to determine the identified portion of the received image extending between the pupil and the corner of the eye represented in the received image where the distance between the pupil and the corner of the eye is greatest,

and wherein said calculation unit is operable to generate texture render data utilizing the identified portion of the received image for which the distance between the pupil and the corner of the eye is greatest.

11. An apparatus for generating a texture rendered model, the apparatus comprising:

a receiver operable to receive an image including a representation of an eye having a corner and a pupil;

an identification unit operable to identify a portion of the image received by said receiver extending between the pupil and the corner of the eye represented in the image;

a copying unit operable to generate texture render data by copying at least some of the identified portion of the received image; and

a calculation unit operable to calculate the remainder of the texture render data utilizing the copied data, such that texture render data at a specified distance from the center of the pupil in the texture render data corresponds to image data from within the identified portion of the received image at a corresponding distance from the center of the pupil in the identified portion of the received image; and

an image generation unit operable to texture render portions of computer generated models by utilizing the texture render data.

12. An apparatus in accordance with claim 11, wherein said image generation unit comprises:

a model generation unit operable to utilize image data received by the receiver to generate a 3D wire mesh model of an individual represented by received image data; and

a texture rendering unit operable to texture render the wire mesh model, wherein said texture rendering unit is arranged to texture render portions of the wire mesh model representing the eyes by utilizing the texture render data.