Abstract
The two-dimensional discrete cosine transform (2-D DCT) has been widely recognized as the most effective technique in image data compression, especially for high-speed video processing applications, such as high-definition television (HDTV). In this paper, we propose a new fully pipelined architecture to compute the 2-D DCT from a frame-recursive point of view. Based on this approach, two real-time parallel lattice structures for successive frame and block 2-D DCT are developed. These structures are fully-pipelined with throughput rate N clock cycles for an N × N successive input data frame. These are the fastest pipelined structures known so far. Moreover, the resulting 2-D DCT architectures are modular, regular, and locally connected and require only two 1-D DCT blocks that are extended directly from the 1-D DCT structure without transposition. It is therefore very suitable for VLSI implementation for high-speed HDTV systems. We also propose a parallel 2-D DCT architecture and a new scanning pattern for HDTV systems to achieve higher performance. The VLSI implementation of the 2-D DCT using distributed arithmetic to increase computational efficiency and reduce round-off error is also discussed. © 1992 IEEE