Method for sharing emotions through the creation of three dimensional avatars and their interaction

• US 9,870,636 B2
• Filed: 08/11/2014
• Issued: 01/16/2018
• Est. Priority Date: 02/13/2012
• Status: Expired due to Fees

• Current Assignee: Mood Me Belgium SPRL
• Original Assignee: Mood Me Belgium SPRL
• Inventors: Tarquini, Massimiliano, De Keyser, Olivier Chandra, Ligi, Allessandro
• Primary Examiner(s): Wilson, Nicholas R
• Application Number:
  US14/456,759
• Publication Number:
  US 20150091896A1
• Time in Patent Office: 1,254 Days
• Field of Search: None
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• 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 2213/04 Animation description language
• CPC Class Codes: H04M 1/72427 for supporting games or graphical animations

Abstract

A two-dimensional image is transformed into at least one portion of a human or animal body into a three-dimensional model. An image is acquired that includes the at least one portion of the human or animal body. An identification is made of the at least one portion within the image. Searches are made for features indicative of the at least one portion of the human or animal body within the at least one portion. One or more identifications are made of a set of landmarks corresponding to the features. An alignment is a deformable mask including the set of landmarks. The deformable mask includes a number of meshes corresponding to the at least one portion of the human or animal body. The 3D model is animated by dividing it into concentric rings, quasi rings and applying different degrees of rotation to each ring.

Claims

1. A computer implemented method for transforming a two-dimensional image of at least one portion of a human or animal body into a deformable mask, comprising:

a) acquiring an image including the at least one portion of the human or animal body;

b) identifying the at least one portion of the human or animal body within the image;

c) searching for features indicative of the at least one portion of the human or animal body within the at least one portion;

d) identifying a set of landmarks corresponding to the features;

e) aligning the deformable mask including the set of landmarks, the deformable mask comprising a number of meshes that correspond to the at least one portion of the human or animal body, wherein a depth corresponding to a mesh of the deformable mask is determined empirically based on the set of landmarks corresponding to the features;

f) applying a plurality of concentric rings to the image, wherein the plurality of concentric rings rotate about a pivot point and include a background concentric ring positioned outside of the at least one portion of the human or animal body and a body concentric ring positioned on the at least one portion of the human or animal body, wherein the background concentric ring includes a first plurality of vertices, and wherein the body concentric ring includes a second plurality of vertices; and

g) animating the deformable mask by applying different degrees of rotation to the first plurality of vertices and the second plurality of vertices, wherein a zero degree of rotation is applied to the first plurality of vertices.

2. The method according to claim 1, wherein the at least one portion of the human or animal body includes at least a face and step c) includes searching for facial features, the set of landmarks corresponding to facial features.

3. The method according to claim 2, further comprising reconstructing non-visible parts of the face.

4. The method according to claim 2, further comprising:

moving points in the deformable mask according to at least one defined storyboard to create complex face animations, each defined storyboard simulating at least one of;

a human or animal emotion.

5. The method according to claim 1, further comprising:

applying an easing function to smooth movements in the animated deformable mask.

6. The method according to claim 1, further comprising:

adjusting the amount of animation in accordance with contours applied to the deformable mask.

7. The method according to claim 1, further comprising:

changing the deformable mask locally on a mobile device.

8. The method according to claim 1, further comprising:

storing the deformable mask on a platform in a cloud environment.