Handheld computer systems and techniques for character and command recognition related to human movements
First Claim
1. A handheld device, comprising:
- inertial sensors comprising a gyroscope that generates gyroscope data representing a trajectory of a movement of the handheld device and an accelerometer that generates accelerometer data representing a tilt of the handheld device relative to earth'"'"'s gravity; and
a processing component that;
determines the trajectory of the movement of the handheld device by combining the gyroscope data representing the trajectory of the movement of the handheld device and the accelerometer data representing the tilt of the handheld device relative to earth'"'"'s gravity;
converts, via a training mode, a first portion of the data into a first set of values corresponding to a first plurality of discrete features,associates the first set of values with a character, stores the first set of values and information representing the character in a training database,converts, via a recognition mode, a second portion of the data into a second set of values corresponding to a second plurality of discrete features, wherein a discrete feature of the first plurality of discrete features or the second plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction; and
in response to a determination that the second set of values matches the first set of values with respect to a defined condition, displays the character.
2 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods for human hand gesture recognition through a training mode and a recognition mode are disclosed. In the training mode, a user can move a handheld device with a hand gesture intended to represent a command. Sensors within the handheld device can record raw data, which can be processed to obtain a set of values corresponding to a set of discrete features, which is stored in a database and associated with the intended command. The process is repeated for various hand gestures representing different commands. In the recognition mode, the user can move the handheld device with a hand gesture. A computer system can compare a set of values corresponding to a set of discrete features derived from the hand gesture with the sets of values stored in the database, select a command with the closest match and displays and/or executes the command.
97 Citations
46 Claims
-
1. A handheld device, comprising:
-
inertial sensors comprising a gyroscope that generates gyroscope data representing a trajectory of a movement of the handheld device and an accelerometer that generates accelerometer data representing a tilt of the handheld device relative to earth'"'"'s gravity; and a processing component that; determines the trajectory of the movement of the handheld device by combining the gyroscope data representing the trajectory of the movement of the handheld device and the accelerometer data representing the tilt of the handheld device relative to earth'"'"'s gravity; converts, via a training mode, a first portion of the data into a first set of values corresponding to a first plurality of discrete features, associates the first set of values with a character, stores the first set of values and information representing the character in a training database, converts, via a recognition mode, a second portion of the data into a second set of values corresponding to a second plurality of discrete features, wherein a discrete feature of the first plurality of discrete features or the second plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction; and in response to a determination that the second set of values matches the first set of values with respect to a defined condition, displays the character. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A method for gesture recognition, comprising:
-
obtaining first training data related to a first trajectory of a first movement of a handheld device using a gyroscope and an accelerometer; determining the first trajectory in response to integrating a portion of the first training data associated with the gyroscope with another portion of the first training data associated with the accelerometer representing a first tilt of the handheld device relative to earth'"'"'s gravity; converting the first training data into first values corresponding to a first set of a plurality of discrete features;
wherein a discrete feature of the plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction;associating the first values with a first character; storing the first values and information representing the first character in a data store; and displaying the first character based on the first values. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
-
21. A handheld device, comprising:
-
a gyroscope; an accelerometer; a processing component that receives gyroscope data from the gyroscope representing a trajectory of a movement of the handheld device and receives accelerometer data from the accelerometer representing a tilt of the handheld device relative to earth'"'"'s gravity; a programmable module coupled to the processing component that includes a look up table that associates a plurality of discrete features comprising the trajectory of the movement of the handheld device and the tilt of the handheld device with a plurality of characters; and a data store for storing a plurality of sets of values corresponding to the plurality of discrete features, wherein the processing component converts a first portion of the data into a first set of values corresponding to first features of the plurality of discrete features, associates, utilizing the look up table, the first set of values with a character of the plurality of characters based on the first features, stores the first set of values and information representing the character in the data store, converts a second portion of the data into a second set of values corresponding to second features of the plurality of discrete features, matches, using the data store, the second set of values to one of the plurality of sets of values, and displays the character using the information, wherein a discrete feature of the plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction. - View Dependent Claims (22, 23, 24)
-
-
25. A method, comprising:
-
obtaining first information from a gyroscope based on a first trajectory of a first movement of a handheld device; storing the first information and authentication information representing an identity of a user in a training data store; obtaining second information from the gyroscope based on a second trajectory of a second movement of the handheld device; in response to determining an orientation of the handheld device utilizing a magnetometer, modifying the first information and the second information according to the orientation;
wherein the first trajectory and the second trajectory are connected to a set of values corresponding to a set of selected discrete features wherein a discrete feature of the plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction;in response to the modifying, comparing the second information with the first information; and authenticating the identity of the user in response to the comparing of the second information with the first information. - View Dependent Claims (26, 27)
-
-
28. A handheld device, comprising:
-
a first processor; a programmable module comprising a look up table that associates a plurality of discrete features representing trajectories of movements of the handheld device with a plurality of commands;
wherein a discrete feature of the plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction; anda gyroscope, wherein the first processor receives at least a portion of first information related to a first movement of the handheld device from the gyroscope, determines the first movement based on the portion, consults the look up table and matches the first movement to a command from the plurality of commands, and wherein a first component coupled to the first processor enters a first active mode of operation from a sleep mode of operation based on the command. - View Dependent Claims (29, 30, 31, 32, 33, 34, 35, 36)
-
-
37. A method, comprising:
-
receiving, by a system comprising a processor, information from a gyroscope regarding a movement of the system; consulting a look up table that associates discrete features representing trajectories of movements of the system with a plurality of commands; wherein a discrete feature of the first plurality of discrete features or the second plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction; matching the movement to a command from the plurality of commands; and switching, based on the command, a component of the system from a sleep mode of operation to an active mode of operation. - View Dependent Claims (38, 39, 40, 41, 42, 43, 44)
-
-
45. A method, comprising:
-
detecting a first position of a mobile phone using a gyroscope; consulting a look up table and matching the first position with a first command corresponding to a first column of the look up table representing a first trajectory of the mobile phone; causing, based on the first command, a component of the mobile phone to enter into a sleep mode of operation; detecting a second position of the mobile phone by using the gyroscope; consulting the look up table and matching the second position with a second command corresponding to a second column of the look up table representing a second trajectory of the mobile phone; causing, based on the second command, the component of the mobile phone to enter into an active mode of operation. - View Dependent Claims (46)
-
Specification