Back to results
US 11,688,120 B2Granted
System and method for creating avatars or animated sequences using human body features extracted from a still image
AssigneeImplementation Apps LLC
InventorsAyla Mandel, David Mandel, Stephen D. Williams
Life of this patent
Estimating the term…
Abstract
A user may create an avatar and/or animated sequence illustrating a particular object or living being performing a certain activity, using images of portions of the object or living being extracted from a still image or set of still images of the object or living being.
Claims30
A method comprising:
- in a system comprising at least one processor communicatively coupled to a display device, for displaying an animated sequence of images, and an image capture device, for capturing one or more still images:
- performing image segmentation on each of the one or more still images, the image segmentation resulting in a generation of one or more sub-images, for each of the one or more still images, in which an object or a living being appears, wherein the image segmentation reduces an amount of image data to be analyzed;
- performing object recognition upon the one or more sub-images to identify composite image portions of the object or the living being;
- extracting image data of the composite image portions from the one or more sub-images;
- analyzing the composite image portions to identify a boundary of the object or the living being;
- applying the composite image portions to corresponding surface portions of a movable mathematical model;
- and
- animating the movable mathematical model according to a motion template, wherein the motion template comprises a time ordered series of vectors for respective reference points of underlying structural features of each of the recognized portions of the object or the living being.
5 more elements
A system comprising:
- one or more processors operably coupled to a display device, the one or more processors operable to:
- perform image segmentation on each of one or more still images, the image segmentation resulting in a generation of one or more sub-images, for each of the one or more still images, in which an object or a living being appears, wherein the image segmentation reduces an amount of image data to be analyzed;
- perform object recognition upon the one or more sub-images to identify composite image portions of the object or the living being;
- extract image data of the composite image portions from the one or more sub-images;
- analyze the composite image portions to identify a boundary of the object or the living being;
- apply the composite image portions to corresponding surface portions of a movable mathematical model;
- and
- animate the movable mathematical model according to a motion template, wherein the motion template comprises a time ordered series of vectors for respective reference points of underlying structural features of each of the recognized portions of the object or the living being.
5 more elements
A non-transitory computer-readable medium having stored thereon, a plurality of code sections, each code section comprising a plurality of instructions executable by one or more processors to cause the one or more processors to perform the actions of a method, the actions comprising:
- performing image segmentation on each of one or more still images, the image segmentation resulting in a generation of one or more sub-images, for each of the one or more still images, in which an object or a living being appears, wherein the image segmentation reduces an amount of image data to be analyzed;
- performing object recognition upon the one or more sub-images to identify composite image portions of the object or the living being;
- extracting image data of the composite image portions from the one or more sub-images;
- analyzing the composite image portions to identify a boundary of the object or the living being;
- applying the composite image portions to corresponding surface portions of a movable mathematical model;
- and
- animating the movable mathematical model according to a motion template, wherein the motion template comprises a time ordered series of vectors for respective reference points of underlying structural features of each of the recognized portions of the object or the living being.
4 more elements
Dependencies are inferred from the claim text.