Facial recognition and transmission of facial images in a videoconference
View Patent ↗Aspects herein describe new methods and systems of receiving one or more images by one or more cameras. Each of the one or more images is acquired by one or more cameras in which the one or more images comprise facial images corresponding to persons. In one embodiment, aspects of the disclosure describe a method for extracting each of the facial images from each of the images in which each of the facial images corresponds to each of one or more sets of extracted facial images. The method further includes sorting each of the extracted facial images per each set into separate groups of one or more groups wherein each group corresponds to facial images of each person. The method further includes selecting a preferred facial image from each group of the one or more groups to generate preferred facial images for transmission to a client using a display server.
1. A system comprising:
one or more cameras;
at least one processor; and
at least one memory for storing computer executable instructions, wherein execution of the computer executable instructions by the at least one processor causes the system to perform a method comprising:
receiving a set of images by at least one of the cameras, wherein individual images in the set of images comprise one or more facial images of one or more persons;
extracting each facial image from the individual images to yield a set of extracted facial images;
sorting individual extracted facial images into one of one or more separate groups wherein individual groups of the one or more groups include the extracted facial images of one of the persons;
selecting, from each group, one of the extracted facial images as a preferred facial image to generate a set of preferred facial images;
transmitting the set of preferred facial images to a display server; and
determining whether a lip area of one of the persons is visible in one of the preferred facial images; and
selecting, based on whether the lip area of one of the persons is visible in one of the preferred facial images, either a facial recognition algorithm or an audio triangulation algorithm to determine which person is speaking.
2. The system of claim 1 wherein method further comprises:
responsive to determining that the lip area of one of the persons is visible in one of the preferred facial images, selecting the facial recognition algorithm to determine which person is speaking;
monitoring lip movements of each of the one or more persons using the facial recognition algorithm;
determining which one of the persons is speaking based on the lip movements; and
visually indicating who is speaking by using a feature of a viewport.
3. The system of claim 2 wherein the computing device comprises one of: a desktop computer, a laptop computer, a wireless phone, and a notepad.
4. The system of claim 1 wherein the amount of data transmitted for each preferred facial image is based on:
a total number of preferred facial images transmitted to the display server per image; and
a bandwidth associated with a connection between the system and the display server.
5. The system of claim 1 wherein each preferred facial image is transmitted in a separate stream to the display server and wherein the set of preferred facial images is displayed on a grid-like pattern on a monitor.
6. The system of claim 1 wherein an optimal width angle and optimal view angle is determined for each camera relative to a particular spatial location.
7. A system comprising:
a computing device; and
one or more first cameras communicatively coupled to the computing device, wherein the computing device comprises:
a second camera;
at least one processor; and
at least one memory for storing computer executable instructions, wherein execution of the computer executable instructions by the at least one processor causes the computing device to perform a method comprising:
receiving a set of first images by at least one of the first cameras, wherein individual first images in the set of first images comprise one or more first facial images of one or more persons;
receiving a second image by the second camera, the second image comprising one or more second facial images of at least one of the persons;
extracting each first facial image from the individual first images to yield a set of extracted first facial images;
extracting each second facial image from the second image to yield a set of extracted second facial images;
sorting individual extracted first facial images and individual extracted second facial images into one of one or more separate groups wherein individual groups include the extracted first or second facial images of one of the persons;
selecting, from each group, one of the extracted first or second facial images as a preferred facial image to generate a set of preferred facial images;
transmitting the set of preferred facial images to a display server;
determining whether a lip area of one of the persons is visible in one of the preferred facial images; and
selecting, based on whether the lip area of one of the persons is visible in one of the preferred facial images, either a facial recognition algorithm or an audio triangulation algorithm to determine which person is speaking.
8. The system of claim 7 wherein the one or more first cameras are communicatively coupled to the computing device by way of using one or more of a: near field communication (NFC) connection, USB connection, IEEE 802.11 connection, and a Bluetooth connection.
9. The system of claim 7 , wherein the one or more first cameras and the second camera are positioned in different locations to allow for different view angles relative to a particular spatial location.
10. The system of claim 7 wherein the preferred facial image is selected based on a comparison with a high resolution control image stored in a database within the computing device.
11. The system of claim 7 wherein each of the one or more preferred facial images is resized based on:
a bandwidth associated with a connection between the computing device and the display server; and
a total number of preferred images transmitted to the display server.
12. The system of claim 7 wherein the computing device comprises one of: a desktop computer, a wireless phone, and a portable notepad.
13. The system of claim 7 wherein each preferred facial image is transmitted as a separate stream to the display server.
14. The system of claim 7 wherein an optimal width angle and optimal view angle is determined for each first camera and the second camera relative to a particular spatial location.
15. A method comprising:
receiving a set of images by one or more cameras, wherein individual images in the set of images comprise one or more facial images of one or more persons;
extracting each facial image from the individual images to yield a set of extracted facial images;
sorting individual extracted facial images into one of one or more separate groups wherein individual groups of one or more groups include the extracted facial images of one of the persons;
selecting, from each group, one of the extracted facial images as a preferred facial image to generate a set of preferred facial images; and
transmitting the set of preferred facial images to a display server;
determining whether a lip area of one of the persons is visible in one of the preferred facial images; and
selecting, based on whether the lip area of one of the persons is visible in one of the preferred facial images, either a facial recognition algorithm or an audio triangulation algorithm to determine which person is speaking;
wherein the extracting, sorting, selectings, transmitting, and determining is performed by at least one processor executing computer executable instructions, wherein the computer executable instructions are stored in at least one memory.
16. The method of claim 15 wherein the method further comprises:
responsive to determining that the lip area of one of the persons is visible in one of the preferred facial images, selecting the facial recognition algorithm to determine which person is speaking;
monitoring lip movements of each of the one or more persons using the facial recognition algorithm;
determining which one of the persons is speaking based on the lip movements; and
visually indicating who is speaking by using a feature of a viewport.
17. The method of claim 16 wherein the computing device comprises one of: a desktop computer, a laptop computer, a wireless phone, and a notepad.
18. The method of claim 15 wherein the amount of data transmitted for each preferred facial image is based on:
a total number of preferred facial images transmitted to the display server per image; and
a bandwidth associated with a connection between the system and the display server.
19. The method of claim 15 wherein each preferred facial image is transmitted in a separate stream to the display server and wherein the set of preferred facial images is displayed on a grid-like pattern on a monitor.
20. The method of claim 15 wherein an optimal width angle and optimal view angle is determined for each camera relative to a particular spatial location.