A 250MHz optimized distributed architecture of 2D 8x8 DCT

Discrete cosine transform (DCT) plays an important role in image and video compression, but computing a two-dimensional (2D) DCT, a large number of multiplications and additions are required in a direct approach. Multiplications, which are the most time-consuming and expensive operations in simple processor, can be completely avoided in our proposed architecture for multiple channel real-time image compression. In this paper, a compressed distributed arithmetic architecture for 2D 8times8 DCT is presented, which offers high speed and small area. The basic architecture consists of a ID row DCT followed by a transpose register array and another ID column DCT, in which an 8-input ID DCT structure only requires 15 adders to build a compressed adder matrix and no ROM is needed. Compared with other architectures available, it has a great improvement on computing speed and reducing area.

[1]  Joan L. Mitchell,et al.  JPEG: Still Image Data Compression Standard , 1992 .

[2]  Magdy A. Bayoumi,et al.  A low power high performance distributed DCT architecture , 2002, Proceedings IEEE Computer Society Annual Symposium on VLSI. New Paradigms for VLSI Systems Design. ISVLSI 2002.

[3]  Earl E. Swartzlander,et al.  DCT Implementation with Distributed Arithmetic , 2001, IEEE Trans. Computers.

[4]  Roger F. Woods,et al.  Implementation of fixed DSP functions using the reduced coefficient multiplier , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).