Vector quantization of images with variable block size
Vector quantization of images with variable block size
复制标题
DOI：
10.1016/j.asoc.2007.05.002
复制
发表时间：
2008-01-01
影响因子：
8.7
通讯作者：
Suzuki, Yukinori
中科院分区：
文献类型：
--
作者：
Sasazaki, Kazuya;Saga, Sato;Suzuki, Yukinori
我们提出了一种使用图像的局部分形维数 (LFD) 的可变块大小的矢量量化 (VQ)。迄今为止，具有可变块大小的AVQ已经使用四叉树（QT）分解算法来实现。 QT分解根据图像局部区域的同质性进行图像划分。然而，我们认为图像局部区域的复杂性比同质性更重要，因为我们更关注复杂区域而不是同质区域。因此，复杂区域对于图像压缩至关重要。由于图像区域的复杂性是通过 LFD 值来量化的，因此我们使用 LFD 值实现了可变块大小，并为 VQ 构建了码本 (CB)。为了确认所提出方法的性能，我们仅使用判别分析和 FGLA 来构建 CB。这里，FGLA是广义Lloyd算法(GLA)和模糊k均值算法相结合的算法。计算实验结果表明，该方法正确编码了我们密切关注的区域。对于获得良好感知的压缩图像来说，这是一个有希望的结果。此外，该方法的性能在压缩率和解码图像质量方面均优于 FGLA 的 VQ。此外，使用该方法仅使用 252 个码向量即可实现 1.0 bpp 和超过 30 dB 的 PSNR。 (C) 2007 Elsevier B.V. 保留所有权利。
We proposed a vector quantization (VQ) with variable block size using local fractal dimensions (LFDs) of an image. AVQ with variable block size has so far been implemented using a quad tree (QT) decomposition algorithm. QT decomposition carries out image partitioning based on the homogeneity of local regions of an image. However, we think that the complexity of local regions of an image is more essential than the homogeneity, because we pay close attention to complex region than homogeneous region. Therefore, complex regions are essential for image compression. Since the complexity of regions of an image is quantified by values of LFD, we implemented variable block size using LFD values and constructed a codebook ( CB) for a VQ. To confirm the performance of the proposed method, we only used a discriminant analysis and FGLA to construct a CB. Here, the FGLA is the algorithm to combine generalized Lloyd algorithm (GLA) and the fuzzy k means algorithm. Results of computational experiments showed that this method correctly encodes the regions that we pay close attention. This is a promising result for obtaining a well-perceived compressed image. Also, the performance of the proposed method is superior to that of VQ by FGLA in terms of both compression rate and decoded image quality. Furthermore, 1.0 bpp and more than 30 dB in PSNR by a CB with only 252 code-vectors were achieved using this method. (C) 2007 Elsevier B.V. All rights reserved.