SYSTEM AND METHODS OF ADAPTIVE SAMPLING FOR EMOTIONAL STATE DETERMINATION

• US 20150356349A1
• Filed: 08/13/2014
• Published: 12/10/2015
• Est. Priority Date: 06/06/2014
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Govindarajeswaran, Maheshwaran, Ghosh, Sudipta, Jeyaprasad Arjun Jeyarani, Arun
• Granted Patent: US 9,323,984 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 40/164 using holistic features
• CPC Class Codes: G06V 40/175 Static expression
• CPC Class Codes: G06V 40/176 Dynamic expression

Abstract

Systems, methods, and non-transitory computer readable media for determining the emotional state of a user are described herein. In one example, the method for determining the emotional state of the user comprises receiving a feed from a sensor at a default sampling frequency, and analyzing the feed to determine facial features of a user. The method further comprises computing an emotional quotient of the user based on the facial features, determining a trigger to re-compute the sampling frequency the feed, based in part on the emotional quotient and computing a new sampling frequency based in part on the trigger. Thereafter, the method comprises generating instructions for the sensor to capture the feed at the new sampling frequency.

Claims

1. An emotion tracking system, comprising:

a processor; and

a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which when executed by the processor, cause the processor to perform steps comprising;

receiving a feed from a sensor at a default sampling frequency;

analyzing the feed to determine facial features of a user;

computing an emotional quotient of the user based on the facial features;

determining a trigger to re-compute the default sampling frequency for the feed, based at least in part on the emotional quotient;

computing a new sampling frequency based at least in part on the trigger; and

generating instructions for the sensor to capture the feed at the new sampling frequency.

2. The emotion tracking system as claimed in claim 1, wherein the processor-executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

ascertaining a cause of the trigger, wherein the cause is at least one of user movement, user emotional transition, or content characterization; and

computing the new sampling frequency based at least in part on the cause.

3. The emotion tracking system as claimed in claim 1, wherein the processor-executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

mapping at least one of the facial features of the user with a list of pre-defined emotion indicators, wherein each of the pre-defined emotion indicators is associated with a weight; and

computing the emotional quotient based at least in part on the mapping.

4. The emotion tracking system as claimed in claim 1, wherein the computing the new sampling frequency further comprises at least one of:

enhancing the default sampling frequency upon determining at least one of user movement or user emotional transition, or

decreasing the default sampling frequency upon determining lack of at least one of user movement or user emotional transition.

5. The emotion tracking system as claimed in claim 1, wherein the processor-executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

associating the user emotional transition with a content being experienced by the user; and

updating a profile of the user based on the association.

6. The emotion tracking system as claimed in claim 5, wherein the processor-executable instructions, when executed by the processor, further cause the processor to perform steps further comprising computing the new sampling frequency based in part on the updated profile of the user.

7. A method for determining the emotional state of a user, the method comprising:

receiving, with an emotion tracking computing device, a feed from a sensor at a default sampling frequency;

analyzing, with the emotion tracking computing device, the feed to determine facial features of a user;

computing, with the emotion tracking computing device, an emotional quotient of the user based on the facial features;

determining, with the emotion tracking computing device, a trigger to re-compute the default sampling frequency for the feed, based at least in part on the emotional quotient;

computing, with the emotion tracking computing device, a new sampling frequency based at least in part on the trigger; and

generating, with the emotion tracking computing device, instructions for the sensor to capture the feed at the new sampling frequency.

8. The method as claimed in claim 7, wherein the method further comprises:

ascertaining, with the emotion tracking computing device, a cause of the trigger, wherein the cause is at least one of user movement, user emotional transition, or content characterization; and

computing, with the emotion tracking computing device, the new sampling frequency based at least in part on the cause.

9. The method as claimed in claim 7, wherein the method further comprises:

mapping, with the emotion tracking computing device, at least one of the facial features of the user with a list of pre-defined emotion indicators, wherein each of the pre-defined emotion indicators is associated with a weight; and

computing, with the emotion tracking computing device, the emotional quotient based at least in part on the mapping.

10. The method as claimed in claim 7, wherein the computing the new sampling frequency further comprises at least one of:

enhancing the default sampling frequency upon determining at least one of user movement or user emotional transition, or

decreasing the default sampling frequency upon determining lack of at least one of user movement or user emotional transition.

11. The method as claimed in claim 7, wherein the method further comprises:

associating, with the emotion tracking computing device, the user emotional transition with a content being experienced by the user; and

updating, with the emotion tracking computing device, a profile of the user based on the association.

12. The method as claimed in claim 11, wherein the method further comprises computing, with the emotion tracking computing device, the new sampling frequency based in part on the updated profile of the user.

13. A non-transitory computer readable medium comprising processor executable instructions, which when executed by a processor cause the processor to perform steps comprising:

receiving a feed from a sensor at a default sampling frequency;

analyzing the feed to determine facial features of a user;

computing an emotional quotient of the user based on the facial features;

determining a trigger to re-compute the default sampling frequency for the feed, based at least in part on the emotional quotient;

computing a new sampling frequency based at least in part on the trigger; and

generating instructions for the sensor to capture the feed at the new sampling frequency.

14. The non-transitory computer readable medium of claim 13, wherein the processor executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

ascertaining a cause of the trigger, wherein the cause is at least one of user movement, user emotional transition, or content characterization; and

computing the new sampling frequency based at least in part on the cause.

15. The non-transitory computer readable medium of claim 13, wherein the processor executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

mapping at least one of the facial features of the user with a list of pre-defined emotion indicators, wherein each of the pre-defined emotion indicators is associated with a weight; and

computing the emotional quotient based at least in part on the mapping.

16. The non-transitory computer readable medium of claim 13, wherein the computing the new sampling frequency further comprises at least one of:

enhancing the default sampling frequency upon determining at least one of user movement or user emotional transition, or

decreasing the default sampling frequency upon determining lack of at least one of user movement or user emotional transition.

17. The non-transitory computer readable medium of claim 13, wherein the processor executable instructions, when executed by the processor, further cause the processor to perform steps further comprising:

associating the user emotional transition with a content being experienced by the user; and

updating a profile of the user based on the association.

18. The non-transitory computer readable medium of claim 13, wherein the processor executable instructions, when executed by the processor, further cause the processor to perform steps further comprising computing the new sampling frequency based in part on the updated profile of the user.