Block-based manipulations on transform-compressed images and videos

Abstract.

This paper addresses the problem of direct image and video manipulation in compressed domain. The capability to perform such manipulations has become attractive in recent years, as more and more visual information is being captured, stored, and moved in compressed form. Our solution to direct manipulation of compressed images and video is based on a set of block-level transforms, called the inner block transforms (IBTs). Each IBT requires a minimal computation effort in compressed domain to yield a regular geometric transformation on an image block. The paper shows how the IBTs can be used to perform many image and video manipulations. This is done by describing the application of IBTs to image subtitling, shearing, and arbitrary angle rotation. The paper also discusses the application of IBT to M-JPEG and MPEG video. The benefits of the proposed direct compressed domain manipulation approach include faster speed, preservation of image quality, and less computing resources.