Hand-over-face input sensing for interaction with a device having a built-in camera
AssigneeHuawei Technologies Co., Ltd.
InventorsMona Hosseinkhani Loorak, Wei Zhou, Wei Li
Life of this patent
Estimating the term…
Abstract
A system including neural network that use deep learning for object detection allows users to interact with images of their face and, in particular, interact with different face landmarks as an input channel for interaction with smart devices. That is, the face is employed as a touch surface for interactions with a device.
Claims20
A method of sensing an interaction with an electronic device comprising a camera, the method comprising:
- receiving image data for one or more images captured by the camera;
- processing the image data for the one or more images to determine a type of a hand gesture and a location of the hand gesture in the one or more images;
- processing the image data for the one or more images to determine a plurality of face landmark locations in the one or more images;
- comparing the location of the hand gesture to each face landmark location in the plurality of face landmark locations;
- identifying, based on the comparing and the type for the hand gesture, an action;
- and
- providing an indication of the action.
An electronic device comprising:
- a camera adapted to capture one or more images;
- a display screen;
- a processor configured to:
- process image data for the one or more images received from the camera to determine a type of a hand gesture and a location of the hand gesture in the one or more images;
- process image data for the one or more images received from the camera to determine a plurality of face landmark locations in the one or more images;
- compare the location of the hand gesture to each face landmark location in the plurality of face landmark locations;
- identify, based on the comparing and the type of the hand gesture, an action;
- and
- provide an indication of the action.
A non-transitory computer-readable medium storing instructions, wherein execution of the instructions causes a processor of an electronic device comprising a camera to:
- receive image data for one or more images captured by the camera;
- process the image data for the one or more images to determine a type of a hand gesture and a location of the hand gesture in the one or more images;
- process the image data for the one or more images to determine a plurality of face landmark locations in the one or more images;
- compare the location of the hand gesture to each face landmark location in the plurality of face landmark locations;
- identify, based on the comparing and the type for the hand gesture, an action;
- and
- provide an indication of the action.
Dependencies are inferred from the claim text.