Emotion recognition in video

1. A method for determining an emotion of an individual comprising:

receiving a video including images;

detecting a face of the individual in the images;

mapping the detected face to a model including at least two separated points in space corresponding to reference emotions, each of the at least two separated points in space representing a plurality of example faces corresponding to one of the reference emotions; and

determining the emotion of the individual from the reference emotions based on a proximity of the detected face to the at least two separated points in space.

2. The method of claim 1 , wherein the at least two separated points in space are separated by a gap and the determining comprises:

determining the emotion of the individual based on which side of the gap the detected face is mapped.

3. The method of claim 1 , further comprising:

locating feature reference points of the detected face;

aligning a virtual face mesh to the detected face based at least in part on the feature reference points; and

finding at least one deformation of the virtual face mesh in one or more of the images;

wherein the mapping comprises mapping reference parameters corresponding to the at least one deformation to the model.

4. The method of claim 1 , wherein the determined emotion is a negative facial emotion.

5. The method of claim 4 , wherein the negative facial emotion includes at least one of anger, stress, frustration, embarrassment, irritation, and annoyance.

6. The method of claim 1 , further comprising:

generating a communication bearing data associated with the determined emotion; and

transmitting the communication bearing data over a communications network.

7. The method of claim 1 , wherein the model is a supervised learning model.

8. The method of claim 1 , wherein the reference emotions include at least two reference emotions selected from the group containing a neutral reference emotion, a negative reference emotion, and a positive reference emotion.

9. A computing device comprising:

at least one processor; and

a memory storing a model and processor-executable codes, the model including at least two separated points in space corresponding to reference emotions, each of the at least two separated points in space representing a plurality of example faces corresponding to one of the reference emotions, and the processor-executable codes, when implemented by the at least one processor, cause the computing device to:

receive a video including images;

detect a face of the individual in the images;

map the detected face to the model; and

determine the emotion of the individual from the reference emotions based on a proximity of the detected face to the at least two separated points in space.

10. The computing device of claim 9 , wherein the at least two separated points in space are separated by a gap and to determine the emotion the memory storing processor-executable codes cause the computing device to:

determine the emotion of the individual based on which side of the gap the detected face is mapped.

11. The computing device of claim 9 , wherein the memory storing processor-executable codes, when implemented by the at least one processor, further cause the computing device to:

locate feature reference points of the detected face;

align a virtual face mesh to the detected face based at least in part on the feature reference points; and

find at least one deformation of the virtual face mesh in one or more of the images;

wherein to map the reference parameters, the memory storing processor-executable codes cause the computing device to map reference parameters corresponding to the at least one deformation to the model.

12. The computing device of claim 9 , wherein the determined emotion is a negative facial emotion.

13. The computing device of claim 12 , wherein the negative facial emotion includes at least one of anger, stress, frustration, embarrassment, irritation, and annoyance.

14. The computing device of claim 9 , wherein the memory storing processor-executable codes, when implemented by the at least one processor, further cause the computing device to:

generate a communication bearing data associated with the determined emotion; and

transmit the communication bearing data over a communications network.

15. The computing device of claim 9 , wherein the model is a supervised learning model.

16. The computing device of claim 9 , wherein the reference emotions include at least two reference emotions selected from the group containing a neutral reference emotion, a negative reference emotion, and a positive reference emotion.

17. A non-transitory processor-readable storage medium storing processor-executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:

receiving a video including images;

detecting a face of the individual in the images;

mapping the detected face to a model including at least two separated points in space corresponding to reference emotions, each of the at least two separated points in space representing a plurality of example faces corresponding to one of the reference emotions; and

determining the emotion of the individual from the reference emotions based on a proximity of the detected face to the at least two separated points in space.

18. The non-transitory processor-readable storage medium of claim 17 storing processor-executable instructions, wherein, when executed by the processor of the machine, the processor-executable instructions cause the machine to perform operations comprising:

locating feature reference points of the detected face;

aligning a virtual face mesh to the detected face based at least in part on the feature reference points; and

finding at least one deformation of the virtual face mesh in one or more of the images;

wherein the mapping comprises mapping reference parameters corresponding to the at least one deformation to the model.

19. The non-transitory processor-readable storage medium of claim 17 storing processor-executable instructions, wherein, when executed by the processor of the machine, the processor-executable instructions cause the machine to perform operations comprising:

generating a communication bearing data associated with the determined emotion; and

transmitting the communication bearing data over a communications network.

20. The non-transitory processor-readable storage medium of claim 1 , wherein the model is a supervised learning model.