Determining digit movement from frequency data

1. An apparatus comprising:

a movement sensor that captures multi-axis movement data corresponding to movement of a user's limb, the movement corresponding to at least one of: translational movement of a sensor and rotational movement of the sensor;

a processor;

a memory that stores code executable by the processor to:

extract one or more frequency features from the multi-axis movement data;

extract digit movement data from the extracted one or more frequency features, wherein extracting digit movement data comprises extracting frequency data having a predetermined feature value from the extracted one or more frequency features; and

determine from the extracted digit movement data whether the multi-axis movement data corresponds to a predetermined motion of a digit.

2. The apparatus of claim 1 , wherein the movement sensor comprises an acceleration sensor that measures translational movement on multiple axes, wherein capturing multi-axis movement data corresponding to movement of a user's limb comprises receiving frequency data from the acceleration sensor.

3. The apparatus of claim 2 , wherein the movement sensor comprises a gyro sensor that measures rotational movement, wherein capturing multi-axis movement data corresponding to movement of a user's limb comprises combining frequency data received from the acceleration sensor with frequency data received from the gyro sensor.

4. The apparatus of claim 1 , wherein the predetermined feature value is a preset frequency range.

5. The apparatus of claim 1 , wherein determining whether the multi-axis movement data corresponds to a predetermined motion of a digit comprises comparing the magnitude of the extracted digit movement data to a threshold value.

6. The apparatus of claim 1 , wherein determining whether the multi-axis movement data corresponds to a predetermined motion of a digit comprises determining whether the extracted digit movement data matches a preset pattern.

7. The apparatus of claim 1 , wherein the processor further performs an action corresponding to the predetermined motion of a digit.

8. The apparatus of claim 7 , wherein the action corresponding to the predetermined motion of a digit is a pointer control command.

9. The apparatus of claim 1 , wherein the one or more frequency features include a frequency corresponding to movement of a limb surface.

10. The apparatus of claim 1 , wherein the limb is an arm and the apparatus is located at a wrist of the user, wherein capturing multi-axis movement data corresponding to movement of a user's limb comprises measuring movement of a surface of the wrist.

11. A method comprising:

captures multi-axis movement data corresponding to movement of a user's limb, the movement corresponding to at least one of: translational movement of a sensor and rotational movement of the sensor;

extracting, by use of a processor, one or more frequency features from the multi-axis movement data;

extracting digit movement data from the extracted frequency features, wherein extracting digit movement data comprises extracting frequency data having a predetermined feature value from the extracted frequency features; and

determining from the extracted digit movement data whether the multi-axis movement data corresponds to a predetermined motion of a digit.

12. The method of claim 11 , wherein extracting frequency data having a predetermined feature value from the extracted frequency features comprises extracting, from the frequency features, a frequency whose predetermined feature value is larger than or equal to a predetermined threshold value.

13. The method of claim 11 , wherein determining whether the multi-axis movement data corresponds to a predetermined motion of a digit comprises comparing the magnitude of the extracted digit movement data to a threshold value.

14. The method of claim 11 , wherein determining whether the multi-axis movement data corresponds to a predetermined motion of a digit comprises determining whether the extracted digit movement data matches a preset pattern.

15. The method of claim 11 , further comprising:

identifying an action corresponding to the predetermined motion of a digit; and

performing the action in response to determining that the multi-axis movement data corresponds to a predetermined motion of a digit.

16. The method of claim 11 , wherein the one or more frequency features include a frequency corresponding to movement of a limb surface.

17. A program product comprising a computer readable storage medium that is not a transitory signal and that stores code executable by a processor, the executable code comprising code to:

measure, at an apparatus, multi-axis movement data corresponding to movement of a user's limb, the movement corresponding to at least one of: translational movement of a sensor and rotational movement of the sensor;

extract one or more frequency features from the multi-axis movement data;

extract digit movement data from the extracted frequency features, wherein extracting digit movement data comprises extracting frequency data having a predetermined feature value from the extracted frequency features;

determine from the extracted digit movement data whether the multi-axis movement data corresponds to a predetermined motion of a digit; and

perform an action corresponding the predetermined motion of a digit, in response to determining that the movement of the limb corresponds to the predetermined motion of a digit.

18. The program product of claim 17 , wherein the limb is an arm and the apparatus is located at a wrist of the user, wherein extracting one or more frequency features from the multi-axis movement data comprises measuring movement of a surface of the wrist.

19. The program product of claim 17 , wherein measuring multi-axis movement data corresponding to movement of a user's limb corresponds to receiving frequency data from an acceleration sensor that detects translational movement, wherein extracting one or more frequency features from the multi-axis movement data comprises extracting a frequency feature from translational acceleration data captured in multiple axes.

20. The program product of claim 17 , wherein measuring multi-axis movement data corresponding to movement of a user's limb corresponds to receiving frequency data from a gyro sensor that detects rotational movement, wherein extracting one or more frequency features from the multi-axis movement data comprises extracting a frequency feature from rotational velocity data captured in multiple axes.