Experiments with single-pass adaptive vector quantization

Summary form only given. Constantinescu and Storer (1994) introduced an adaptive vector quantization algorithm (AVQ) that combines adaptive dictionary techniques with vector quantization (VQ). The algorithm typically equals or exceeds the compression of the JPEG standard on different classes of images and it often outperforms traditional trained VQ. We show how it is possible to improve AVQ on the class of images on which JPEG does best (i.e., “magazine photographs”). The improvement is possible by exploring the similarities in the dictionary built by AVQ. This is achieved by transforming the input vectors in a way similar to the one used in mean-shape-gain VQ (Oehler and Gray, 1993). In MSGVQ each vector x¯∈Rⁿ is decomposed as x¯=g·s¯+E _x·1¯, where g=||x¯-E_x·1¯|| and s¯=(x¯-E _x·1¯)/g; mean, gain and shape ⟨E_x,g,s¯⟩ are quantized separately. We apply this idea to AVQ, changing the match heuristic: let ⟨E_b,g_b,S¯_b⟩ and ⟨E _p,g_p,S¯_p⟩ be respectively the ⟨mean, gain, shape⟩ of the dictionary block b and of the one anchored in p. The entry b is the best match if d(x¯_p,xˆ)⩽T (xˆ=g_p·s¯_b+E_p ·1¯) and its size is maximum. The triple ⟨b,E_p,g_b⟩ is entropy coded and sent to the decoder. This simple modification of the match heuristic allows AVQ to improve the compression ratio on many images. In some cases this improvement is as high as 60%. Along with the better compression results, there is also an improvement in the overall visual quality of the decoded image, especially at high compression rate