Systems and methods for interactive image caricaturing by an electronic device
AssigneeQUALCOMM Incorporated
InventorsXuan Zou, Fan Ling, Ning Bi, Lei Zhang
Life of this patent
Estimating the term…
Abstract
A method for interactive image caricaturing by an electronic device is described. The method includes detecting at least one feature location of an image. The method further includes generating, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line. The method additionally includes obtaining a gesture input. The method also includes determining at least one caricature action based on the at least one gesture input. The method further includes generating a caricature image based on the image mesh, the at least one caricature action and the image.
Claims46
A method for interactive image caricaturing by an electronic device, comprising:
- detecting at least one feature location of an image;
- generating, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line, wherein at least one vertex of the image mesh corresponds to a feature location of a facial component in the image;
- obtaining at least one gesture input;
- determining at least one caricature action based on the at least one gesture input, wherein the caricature action provides a pixel map that maps an image vertex pixel of the at least one vertex to a corresponding caricature image vertex pixel;
- and
- generating a caricature image based on the image mesh, the at least one caricature action and the image.
An electronic device for interactive image caricaturing, comprising:
- feature location detection circuitry configured to detect at least one feature location of an image;
- image mesh generation circuitry coupled to the feature location detection circuitry, wherein the image mesh generation circuitry is configured to generate, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line, wherein at least one vertex of the image mesh corresponds to a feature location of a facial component in the image;
- sensing circuitry configured to obtain at least one gesture input;
- caricature action determination circuitry coupled to the sensing circuitry, wherein the caricature action determination circuitry is configured to determine at least one caricature action based on the at least one gesture input, wherein the caricature action provides a pixel map that maps an image vertex pixel of the at least one vertex to a corresponding caricature image vertex pixel;
- and
- caricature image generation circuitry coupled to the image mesh generation circuitry and the caricature action determination circuitry, wherein the caricature image generation circuitry is configured to generate a caricature image based on the image mesh, the at least one caricature action and the image.
A non-transitory tangible computer-readable medium having instructions thereon, the instructions comprising:
- code for causing an electronic device to detect at least one feature location of an image;
- code for causing the electronic device to generate, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line, wherein at least one vertex of the image mesh corresponds to a feature location of a facial component in the image;
- code for causing the electronic device to obtain at least one gesture input;
- code for causing the electronic device to determine at least one caricature action based on the at least one gesture input, wherein the caricature action provides a pixel map that maps an image vertex pixel of the at least one vertex to a corresponding caricature image vertex pixel;
- and
- code for causing the electronic device to generate a caricature image based on the image mesh, the at least one caricature action and the image.
An apparatus for interactive image caricaturing, comprising:
- means for detecting at least one feature location of an image;
- means for generating, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line, wherein at least one vertex of the image mesh corresponds to a feature location of a facial component of the image;
- means for obtaining at least one gesture input;
- means for determining at least one caricature action based on the at least one gesture input, wherein the caricature action provides a pixel map that maps an image vertex pixel of the at least one vertex to a corresponding caricature image vertex pixel;
- and
- means for generating a caricature image based on the image mesh, the at least one caricature action and the image.
Dependencies are inferred from the claim text.