An efficient weight optimization algorithm for image representation using nonorthogonal basis vectors

Though image-coding techniques that employ subsets of nonorthogonal basis images chosen from two or more transform domains have been shown consistently to yield higher image quality than those based on one transform for a fixed compression ratio, they have not been widely employed due to their very high computational complicity of existing realization approaches. This paper presents a new realization approach for mixed-transform image representation. Computational complexity can be greatly reduced compared with existing approaches.