Concepts from artificial intelligence and learning theory are proposed for use in a knowledge-based true information TV (TITV) system. In a knowledge-based TV system a store of images is learned prior to transmission. In learn mode an image from a television camera is stored into an encoding list which is then copied to a retrieval list at the receiver. The resulting transmission bandwidth is not dependent on screen size, resolution, or scanning rate but rather only on novelty and movement. The moving portion of the input image is compared with previously learned image sections to generate superpixel codes for transmission. A superpixel may contain any size image section, from single pixel to entire images. Digital superpixel transmission promises near-perfect images for high-definition TV (HDTV) at orders of magnitude lower bandwidth and, if desired, in a virtually unbreakable encryption code.
展开▼
