Browse Prior Art Database

A System and Method to Enable Low-Cost Network Transmission Bandwidth to Transfer Videos of a Face

IP.com Disclosure Number: IPCOM000246582D
Publication Date: 2016-Jun-20
Document File: 2 page(s) / 50K

Publishing Venue

The IP.com Prior Art Database

Abstract

A system and method is disclosed to enable low-cost network transmission bandwidth to transfer videos of a face. The method and system extracts and transforms necessary facial landmarks at a transmission end. Thereafter, the method reproduces an image of the face transmitted using manipulation of a static picture of the face (transmitted once).

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 2

A System and Method to Enable Low - Transfer Videos of a Face

Disclosed is a system and method to enable low-cost network transmission bandwidth to transfer videos of a face. The method and system extracts and transforms necessary facial landmarks at a transmission end. Thereafter, the method reproduces an image of the face transmitted using manipulation of a static picture of the face (transmitted once).

Following figure illustrates the steps for enabling low-cost network transmission bandwidth to transfer video of a face.

Figure

In accordance with the method and system, an image of the face of a sender peer is transmitted just once to a receiver peer. Thereafter, the system extracts facial landmarks of the sender peer and transmits the extracted facial landmarks to the receiver peer. Subsequently, at the reception device, a face image is reconstructed using the received facial landmarks. Accordingly, the image (original) is modified to reflect the facial landmarks.

In similar manner, an emoticon can be modified based on the extracted facial landmarks and displayed to the receiver peer.

Consider an exemplary scenario wherein user A is reading news on TV. The TV audio is also transmitted into the radio. Another user B has a radio (powered by the system disclosed herein). In accordance with the method disclosed herein, user A's face is transferred once (not too expensive) to user B's radio. Next, facial landmarks of user A are streamed as the user A continues reading news. On user B's device, face of user A is reconstructed graphically, using third-party graphics algorithms, shaped up based upon the facial landmarks received. This gives user B an impression of watching the TV, where only the face of the news...