Assessing human reaction to a stimulus using computer vision

• US 9,734,510 B1
• Filed: 07/11/2012
• Issued: 08/15/2017
• Est. Priority Date: 02/20/2005
• Status: Expired due to Fees

• Current Assignee: Sensory Logic Incorporated
• Original Assignee: Sensory Logic Incorporated
• Inventors: Hill, Daniel A.
• Primary Examiner(s): Yao, Sam
• Assistant Examiner(s): Carlos, Alvin
• Application Number:
  US13/546,805
• Time in Patent Office: 1,861 Days
• Field of Search: 434236, 434322, 434323, 434350
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods for assessing human reaction to a stimulus using computer vision are described herein. A computer can compare a first facial image with a second facial image to identify a region of a subject'"'"'s face where an expressional repositioning is evident. Based on the expressional repositioning, the computer can determine an emotion exhibited by the subject.

Claims

1. A non-transitory machine-readable medium including instructions, which when executed by a machine, cause the machine to perform operations comprising:

comparing a first facial image with a second facial image to identify a region of a face of a subject where an expressional repositioning is evident; and

determining an emotion exhibited by the subject by creating a weighted emotional value from the identified region.

2. The machine-readable storage medium of claim 1, wherein the first facial image and the second facial image are chronologically ordered, and wherein the first facial image corresponds to the face prior to exposure of the subject to an identified stimulus and the second facial image corresponds to the face following exposure of the subject to the identified stimulus.

3. The machine-readable storage medium of claim 1, wherein determining an emotion exhibited by the subject includes coding the identified region to an action unit.

4. The machine-readable storage medium of claim 3, wherein the action units are FACS action units.

5. The machine-readable storage medium of claim 3, wherein the action units are EMFACS action units.

6. The machine-readable storage medium of claim 1, wherein the weighted emotional value includes a weight based on a duration of the expressional repositioning.

7. The machine-readable storage medium of claim 1, wherein the weighted emotional value includes an indication of the impact the stimulus had on the subject.

8. The machine-readable storage medium of claim 7, wherein the impact is at least one of favorable or unfavorable.

9. A method comprising:

comparing, using a hardware processor, a first facial image with a second facial image to identify a region of a face of a subject where an expressional repositioning is evident; and

determining, using the hardware processor, an emotion exhibited by the subject by creating a weighted emotional value from the identified region.

10. The method of claim 9, wherein the first facial image and the second facial image are chronologically ordered, and wherein the first facial image corresponds to the face prior to exposure of the subject to an identified stimulus and the second facial image corresponds to the face following exposure of the subject to the identified stimulus.

11. The method of claim 9, wherein determining an emotion exhibited by the subject includes coding the identified region to an action unit.

12. The method of claim 11, wherein the action units are FACS action units.

13. The method of claim 11, wherein the action units are EMFACS action units.

14. The method of claim 9, wherein the weighted emotional value includes a weight based on a duration of the expressional repositioning.

15. The method of claim 9, wherein the weighted emotional value includes an indication of the impact the stimulus had on the subject.

16. The method of claim 15, wherein the impact is at least one of favorable or unfavorable.

17. A device comprising:

a hardware processor; and

a memory, the memory including instructions, which when executed by the hardware processor, cause the device to;

compare a first facial image with a second facial image to identify a region of a face of a subject where an expressional repositioning is evident; and

determine an emotion exhibited by the subject by creating a weighted emotional value from the identified region.

18. The device of claim 17, wherein the first facial image and the second facial image are chronologically ordered, and wherein the first facial image corresponds to the face prior to exposure of the subject to an identified stimulus and the second facial image corresponds to the face following exposure of the subject to the identified stimulus.

19. The device of claim 17, wherein to determine an emotion exhibited by the subject includes the memory including instructions to cause the device to code the identified region to an action unit.

20. The device of claim 17, wherein the weighted emotional value including a weight based on a duration of the expressional repositioning, and the weighted emotional value including an indication of the impact the stimulus had on the subject, where the impact is at least one of favorable or unfavorable.