Ultrasound based air-writing system and method
AssigneeKing Abdullah University of Science and Technology
InventorsHui Chen, Tarig Ballal Khidir Ahmed, Tareq Yousef Al-Naffouri
Life of this patent
Estimating the term…
Abstract
A method for motion tracking and text recognition, the method including a step of generating ultrasound waves with a transmitter; a step of receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves; a step of estimating with a processor, angle-of-arrival information for the ultrasound waves; a step of associating the angle-of-arrival information with a gesture; a step of extracting features from the gesture; and a step of classifying the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates.
Claims16
A method for motion tracking and text recognition, the method comprising:
- generating ultrasound waves with a transmitter;
- receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves;
- estimating with a processor, angle-of-arrival information for the ultrasound waves, wherein the angle-of-arrival information includes a horizontal angle and a vertical angle of the transmitter relative to the receiver;
- associating the angle-of-arrival information with a gesture;
- extracting features from the gesture, wherein the features correspond to a vector obtained from the horizontal and vertical angles;
- and
- classifying, based on redundant dictionary matching, the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates,
- wherein the one or more templates for the redundant dictionary matching are described by a matrix having a dimension n times M times 2K, with M being a number of the known text characters, n being a number of variations of each known text character, K being a number of samples of each gesture, and 2 corresponding to the horizontal and vertical angles, and
- wherein the number n of variations of the each known character is obtained by shift and shrink of the each known character, which is associated with changing corresponding values of the horizontal and vertical angles of the each known character.
A computing device for motion tracking and text recognition, the computing device comprising:
- a receiver having sensors that record ultrasound waves associated with a gesture;
- an input/output interface configured to receive the ultrasound waves recorded with the receiver;
- and
- a processor configured to
- estimate angle-of-arrival information for the ultrasound waves, wherein the angle-of-arrival information includes a horizontal angle and a vertical angle of the transmitter relative to the receiver,
- associate the angle-of-arrival information with the gesture,
- extract features from the gesture, wherein the features correspond to a vector obtained from the horizontal and vertical angles, and
- classify, based on redundant dictionary matching, the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates,
- wherein the one or more templates for the redundant dictionary matching are described by a matrix having a dimension n times M times 2K, with M being a number of the known text characters, n being a number of variations of each known text character, K being a number of samples of each gesture, and 2 corresponding to the horizontal and vertical angles, and
- wherein the number n of variations of the each known character is obtained by shift and shrink of the each known character, which is associated with changing corresponding values of the horizontal and vertical angles of the each known character.
A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, implement instructions for motion tracking and text recognition, the instructions comprising:
- generating ultrasound waves with a transmitter;
- receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves;
- estimating with a processor, angle-of-arrival information for the ultrasound waves, wherein the angle-of-arrival information includes a horizontal angle and a vertical angle of the transmitter relative to the receiver;
- associating the angle-of-arrival information with a gesture;
- extracting features from the gesture, wherein the features correspond to a vector obtained from the horizontal and vertical angles;
- and
- classifying, based on redundant dictionary matching, the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates,
- wherein the one or more templates for the redundant dictionary matching are described by a matrix having a dimension n times M times 2K, with M being a number of the known text characters, n being a number of variations of each known text character, K being a number of samples of each gesture, and 2 corresponding to the horizontal and vertical angles, and
- wherein the number n of variations of the each known character is obtained by shift and shrink of the each known character, which is associated with changing corresponding values of the horizontal and vertical angles of the each known character.
Dependencies are inferred from the claim text.