SIGNAL PROCESSING DEVICE AND SIGNAL PROCESSING METHOD

• US 20140285427A1
• Filed: 03/12/2014
• Published: 09/25/2014
• Est. Priority Date: 03/21/2013
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Katsuyama, Yutaka, Hotta, Yoshinobu, Minagawa, Akihiro, TAKEBE, HIROAKI
• Granted Patent: US 9,342,152 B2
• Time in Patent Office: Days
• US Class Current: 345/156
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text

Abstract

A signal processing device includes: a memory; and a processor coupled to the memory and configured to: detect a second feature value relating to a first feature value recognized to satisfy a recognition condition, from a second time series prior to a first time series of the first feature value in a times series of a feature value corresponding to an input signal, and change the recognition condition so that the second feature value is recognized as a class for recognizing the first feature value.

Claims

1. A signal processing device comprising:

a memory; and

a processor coupled to the memory and configured to;

detect a second feature value relating to a first feature value recognized to satisfy a recognition condition, from a second time series prior to a first time series of the first feature value in a times series of a feature value corresponding to an input signal, and

change the recognition condition so that the second feature value is recognized as a class for recognizing the first feature value.

2. The signal processing device according to claim 1, wherein

the processor is configured to detect the second feature value when a correlation between the first feature value and the second feature value is higher than or equal to a given threshold.

3. The signal processing device according to claim 1, wherein

the processor is configured to:

detect one or more candidate sections from the second time series based on a similarity to the first feature value, and

select a section including the second feature value from among the one or more candidate sections.

4. The signal processing device according to claim 3, wherein

the processor is configured to detect the one or more candidate sections based on at least one of a detection order on a time axis and a given number with respect to the similarity.

5. The signal processing device according to claim 4, wherein

the processor is configured to detect the one or more candidate sections including one of a candidate section first detected on the time axis or and a candidate section last detected on the time axis.

6. The signal processing device according to claim 1, wherein

the processor is configured to:

set the recognition condition to correspond with a user,

identify a user who has entered the input signal, and

change the recognition condition with respect to the identified user.

7. The signal processing device according to claim 1, wherein

the processor is configured to restore the changed recognition condition to the recognition condition before the change, when at least one of a given period of time has elapsed, a given action has been completed, and an instruction from a user has been provided.

8. The signal processing device according to claim 1, wherein

the input signal indicates an instruction from a user for an operation, and the class corresponds to a content of the operation.

9. The signal processing device according to claim 1, wherein

the processor is configured to change the recognition condition when the second feature value has not been recognized using the recognition condition before the change.

10. The signal processing device according to claim 1, wherein

the second feature value is detected when the second feature value is determined to be within a range of the recognition condition for recognizing the first feature value.

11. The signal processing device according to claim 1, wherein

the processor is configured to recognize a class for the feature value corresponding to the input signal using the changed recognition condition.

12. The signal processing device according to claim 1, wherein

the second feature value is used to recognize a subsequent input signal as satisfying the recognition condition.

13. A signal processing method comprising:

detecting a second feature value relating to a first feature value recognized to satisfy a recognition condition, from a second time series prior to a first time series of the first feature value in a times series of a feature value corresponding to an input signal; and

changing, by a processor, the recognition condition so that the second feature value is recognized as a class for recognizing the first feature value.

14. The signal processing method according to claim 13, wherein

the detecting includes detecting detect the second feature value when a correlation between the first feature value and the second feature value is higher than or equal to a given threshold.

15. The signal processing method according to claim 13, further comprising:

detecting one or more candidate sections from the second time series based on a similarity to the first feature value; and

selecting a section including the second feature value from among the one or more candidate sections.

16. The signal processing method according to claim 15, further comprising:

detecting the one or more candidate sections based on at least one of a detection order on a time axis and a given number with respect to the similarity.

17. The signal processing method according to claim 16, further comprising:

detecting the one or more candidate sections including one of a candidate section first detected on the time axis or and a candidate section last detected on the time axis.

18. The signal processing method according to claim 13, further comprising:

setting the recognition condition to correspond with a user;

identify a user who has entered the input signal; and

changing the recognition condition with respect to the identified user.

19. The signal processing method according to claim 13, further comprising:

restoring the changed recognition condition to the recognition condition before changing, when at least one condition is satisfied among conditions that a given period of time has elapsed, that a given action has been completed, and that an instruction from the user has been provided.

20. A computer-readable storage medium storing a signal processing program for causing a computer to execute a process, the process comprising:

detecting a second feature value relating to a first feature value recognized to satisfy a recognition condition, from a second time series prior to a first time series of the first feature value in a times series of a feature value corresponding to an input signal; and

changing the recognition condition so that the second feature value is recognized as a class for recognizing the first feature value.