Adjusting an image for video conference display
View Patent ↗A video conferencing system contains one or more display adjusting components, whereby an object to be displayed can be adjusted to appropriately fit various sized display screens. A display adjusting component is contained within the sending client, which adjusts the image of the object to be appropriately displayed to one or more receiving clients. The receiving clients also contain a display adjusting component, which can further adjust the image of the object to be displayed, as necessary. The multimedia conferencing server of the video conferencing system also contains a display adjusting component, which negotiates parameters of the sending and receiving clients. Any of the display adjusting components can function alone, or in any combination together. A method, and computer readable media which contain computer readable instructions to perform a method, of adjusting an image for video conference display are also described.
1. A method of displaying an image for video conference display, the method comprising:
identifying feature points of an image;
organizing the feature points to form an outline of one or more shapes in the image;
comparing the outlines to models for various types of objects;
determining a type of object represented by the feature points based on the matches identified in response to the comparison; and
providing the outline of the feature points for display, wherein a display size of the type of object is applied to the outline corresponding to the feature points.
2. The method of claim 1 , wherein the models include portraits of a face.
3. The method of claim 1 , wherein the models include outlines of an article.
4. The method of claim 1 , further comprising modifying the size of the outline corresponding to the feature points of the image based on the distance an element represented by the image is from an image capture device.
5. The method of claim 1 , further comprising modifying the size of the outline corresponding to the feature points of the image based on whether an element represented by the image is associated with speech data.
6. The method of claim 5 , further comprising increasing the size of the outline corresponding to the feature points of the image when the element represented by the image is associated with speech data.
7. The method of claim 1 , further comprising identifying a size and geometry of feature points in the image.
8. The method of claim 7 , further comprising locating eyes, eye brows, and a mouth based on the size and geometry of feature points in the image.
9. One or more non-transitory computer-storage media configured to execute a method of displaying an image for video conference display, the method comprising:
identifying feature points of an image;
organizing the feature points to form an outline of one or more shapes in the image;
comparing the outlines to models for various types of objects;
determining a type of object represented by the feature points based on the matches identified in response to the comparison; and
providing the outline of the feature points for display, wherein a display size of the type of object is applied to the outline corresponding to the feature points.
10. The media of claim 9 , wherein the models include portraits of a face.
11. The media of claim 9 , wherein the models include outlines of an article.
12. The media of claim 9 , further comprising modifying the size of the outline corresponding to the feature points of the image based on the distance an element represented by the image is from an image capture device.
13. The media of claim 9 , further comprising modifying the size of the outline corresponding to the feature points of the image based on whether an element represented by the image is associated with speech data.
14. The media of claim 13 , further comprising increasing the size of the outline corresponding to the feature points of the image when the element represented by the image is associated with speech data.
15. The media of claim 13 , further comprising identifying a size and geometry of feature points in the image.
16. The method of claim 15 , further comprising locating eyes, eye brows, and a mouth based on the size and geometry of feature points in the image.
17. A server having processor and non-transitory computer-storage media configured to execute a method of displaying an image for video conference display, the method comprising:
identifying feature points of an image;
organizing the feature points to form an outline of one or more shapes in the image;
comparing the outlines to models for various types of objects;
determining a type of object represented by the feature points based on the matches identified in response to the comparison; and
providing the outline of the feature points for display, wherein a display size of the type of object is applied to the outline corresponding to the feature points.
18. The method of claim 17 , wherein the models include portraits of a face.
19. The method of claim 17 , wherein the models include outlines of an article.
20. The method of claim 17 , further comprising modifying the size of the outline corresponding to the feature points of the image based on the distance an element represented by the image is from an image capture device.