Human Vision System's Region of Interest Based Video Coding

While watching a video human visual system gives more attention on the foreground objects than background objects. That is to say, human vision system pays more attention to region of interest, such as the human faces in the video content. Most of the video encoders compress video by considering every part of the video frames with equal importance. So the video size could not be reduced to maintain quality. The proposed system can detect the foreground and it can allocate different bit rates for different regions. By doing this the video quality can be maintained and the size can be reduced up to 40%.