Emotion recognition in video conferencing
Methods and systems for videoconferencing include recognition of emotions related to one videoconference participant such as a customer. This ultimately enables another videoconference participant, such as a service provider or supervisor, to handle angry annoyed, or distressed customers. One example method includes the steps of receiving a video that includes a sequence of images, detecting at least one object of interest (e.g., a face), locating feature reference points of the at least one object of interest, aligning a virtual face mesh to the at least one object of interest based on the feature reference points, finding over the sequence of images at least one deformation of the virtual face mesh that reflect face mimics, determining that the at least one deformation refers to a facial emotion selected from a plurality of reference facial emotions, and generating a communication bearing data associated with the facial emotion.
1. A computer-implemented method comprising:
receiving, by one or more processors, information about a conference between a plurality of participants including a first user and a second user;
in an automated operation, based on the received information, determining an emotion of the first user;
determining that the emotion of the first user is a negative emotion; and
in response to determining that the emotion is the negative emotion, generating a communication for transmission to a non-participant of the conference, the communication comprising data associated with the negative emotion.
2. The method of claim 1 , wherein the received information about the conference comprises a video including a sequence of images corresponding to a videoconference, further comprising:
detecting at least one object of interest in one or more of the images;
locating feature reference points of the at least one object of interest; and
determining that at least one deformation between two or more of the feature reference points refers to a facial emotion selected from a plurality of reference facial emotions, wherein the negative emotion is determined from the selected facial emotion.
3. The method of claim 2 , further comprising:
aligning a virtual face mesh to the at least one object of interest based at least in part on the feature reference points; and
finding at least one facial deformation of the virtual face mesh associated with at least one facial mimic.
4. The method of claim 2 , wherein determining that the at least one deformation refers to a facial emotion further comprises:
comparing the deformation between two or more feature reference points to reference facial parameters of the plurality of facial emotions; and
selecting the facial emotion based on the comparison of the deformation between two or more feature reference points to the reference facial parameters.
5. The method of claim 1 , wherein the first user is a service provider and the non-participant is a third party, further comprising:
establishing a videoconference between the service provider and the second user associated with the negative emotion; and
transmitting the communication over a communications network to the third party.
6. The method of claim 1 , wherein the first user is a service provider and the non-participant is a third party, further comprising:
establishing a videoconference between the service provider, the second user, and the third party, the videoconference including the third party being established responsive to determining the negative emotion.
7. The method of claim 1 , further comprising:
detecting one or more gestures; and
determining the one or more gestures are associated with the negative emotion.
8. The method of claim 1 , wherein the information includes an audio stream corresponding to the conference.
9. The method of claim 8 further comprising:
extracting at least one voice feature from the audio stream;
comparing the extracted at least one voice feature to a plurality of reference voice features; and
detecting that the emotion of the first user is the negative emotion based on the comparison.
10. The method of claim 1 , wherein detecting that the emotion of the first user is the negative emotion based on a combination of detecting a facial emotion and a speech emotion of the first user.
11. A system comprising:
one or more processors; and
a non-transitory processor-readable medium coupled to the one or more processors, the non-transitory processor-readable medium comprising processor-executable instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
receiving information about a conference between a plurality of participants including a first user and a second user;
in an automated operation, based on the received information, determining an emotion of the first user;
determining that the emotion of the first user is a negative emotion; and
in response to determining that the emotion is the negative emotion, generating a communication for transmission to a non-participant of the conference, the communication comprising data associated with the negative emotion.
12. The system of claim 11 , wherein the received information about the conference comprises a video including a sequence of images corresponding to a videoconference, and wherein the operations further comprise:
detecting at least one object of interest in one or more of the images;
locating feature reference points of the at least one object of interest; and
determining that at least one deformation between two or more of the feature reference points refers to a facial emotion selected from a plurality of reference facial emotions, wherein the negative emotion is determined from the selected facial emotion.
13. The system of claim 12 , wherein the operations further comprise:
aligning a virtual face mesh to the at least one object of interest based at least in part on the feature reference points; and
finding at least one facial deformation of the virtual face mesh associated with at least one facial mimic.
14. The system of claim 12 , wherein the operations further comprise:
comparing the deformation between two or more feature reference points to reference facial parameters of the plurality of facial emotions; and
selecting the facial emotion based on the comparison of the deformation between two or more feature reference points to the reference facial parameters.
15. The system of claim 11 , wherein the first user is a service provider and the non-participant is a third party, and wherein the operations further comprise:
establishing a videoconference between the service provider and the second user associated with the negative emotion; and
transmitting the communication over communications network to the third party.
16. The system of claim 11 , wherein the first user is a service provider and the non-participant is a third party, and wherein the operations further comprise:
establishing a videoconference between the service provider, the second user, and the third party, the videoconference including the third party being established responsive to determining the negative emotion.
17. The system of claim 11 , wherein the operations further comprise:
detecting one or more gestures; and
determining the one or more gestures are associated with the negative emotion.
18. A non-transitory processor-readable medium comprising processor-executable instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
receiving information about a conference between a plurality of participants including a first user and a second user;
in an automated operation, based on the received information, determining an emotion of the first user;
determining that the emotion of the first user is a negative emotion; and
in response to determining that the emotion is the negative emotion, generating a communication for transmission to a non-participant of the conference, the communication comprising data associated with the negative emotion.
19. The non-transitory processor-readable medium of claim 18 , wherein the received information about the conference comprises a video including a sequence of images corresponding to a videoconference, and wherein the operations further comprise:
detecting at least one object of interest in one or more of the images;
locating feature reference points of the at least one object of interest; and
determining that at least one deformation between two or more of the feature reference points refers to a facial emotion selected from a plurality of reference facial emotions, wherein the negative emotion is determined from the selected facial emotion.
20. The non-transitory processor-readable medium of claim 19 , wherein the operations further comprise:
aligning a virtual face mesh to the at least one object of interest based at least in part on the feature reference points; and
finding at least one facial deformation of the virtual face mesh associated with at least one facial mimic.