An Efficient VLSI Linear Array for DCT/IDCT Using Subband Decomposition Algorithm

Abstract

Discrete Cosine transform (DCT) and inverse DCT (IDCT) have been widely used in many image processing systems and real-time computation of nonlinear time series. In this paper, a novel lineararray of DCT and IDCT is derived from the data flow of subband decompositions representing the factorized coefficient matrices in the matrix formulation of the recursive algorithm. For increasing the throughput as well as decreasing the hardware cost, the input and output data are reordered. The proposed 8-point DCT/IDCT processor with four multipliers, simple adders, and less registers and ROM storing the immediate results and coefficients, respectively, has been implemented on FPGA (field programmable gate array) and SoC (system on chip). The linear-array DCT/IDCT processor with the computation complexityO(5N/8)and hardware complexityO(5N/8)is fully pipelined and scalable for variable-length DCT/IDCT computations.

A novel VLSI linear array for 2-D DCT/IDCT

“…TABLE III shows comparisons between the proposed architecture and other commonly used architectures [8][9][10], [14]. The proposed architectures require 3 multipliers and 21 adders.…”

“…A length-N input sequence , with N being even, can be decomposed into and [14], which denote the low-frequency and high-frequency sub-band signals of , respectively, are defined as The discrete cosine transform (DCT) and inverse DCT (IDCT) are the most widely used transforms in the image and signal processing due to the near optimal performance. The conventional DCT architectures using distributed arithmetic involve complex hardware with high computation complexity [1][2][3][4][5][6][7][8][9][10].…”

“…There are no rules can be found to extend to variable-length DCT and IDCT. A subband decomposition algorithm is used to evaluate both DCT and IDCT in Sung [14]. The proposed architecture still greatly optimizes the computation complexity and hardware complexity [14].…”

“…A subband decomposition algorithm is used to evaluate both DCT and IDCT in Sung [14]. The proposed architecture still greatly optimizes the computation complexity and hardware complexity [14]. In this paper, the novel architectures for onedimension (1-D) 8-point DCT/IDCT and two-dimension (2-D) 8×8 DCT/IDCT based on the sub-band decomposition algorithm are proposed.…”

“…The DCT/IDCT computation proposed by Sung [14] takes twenty multiplication operations for both DCT and IDCT.…”