Abstract: An efficient implementation of n-point discrete cosine transform, n-point inverse discrete cosine transform, shape adaptive discrete cosine transform and shape adaptive inverse discrete cosine transform algorithms for multimedia compression and decompression optimization. An n-point DCT function is represented by a first equation having an input matrix, an output matrix and a matrix of predetermined values. An n-point IDCT function is represented by a second equation having an input matrix, an output matrix and a matrix of predetermined values. The multiplication operations within the matrix of predetermined values are paired, thereby reducing processor instructions. SIMD operations, MMX operations, VLSI implementation, single processor implementation, and vector processing are used to perform the algorithms.

Abstract: A pixel padding procedure is disclosed. The padding procedure provides a method for filling pixels in a block in accordance with intensities of pixels in preceding and succeeding pixels of the same row or column. This padding procedure may include filling pixels with simultaneous logic operations; transposing blocks before and after horizontal padding; case detecting for simple or complex padding; simple pixel filling, where no pixels need to be averaged; and complex pixel filling, which contains pixels to be averaged. In one embodiment, this procedure may be performed in an MMX™ implementation for MPEG-4 repetitive padding.