一种改进的AEI算法中初始匹配码字的快速查找方法

矢量量化（VQ）是一种高效的有损压缩技术。快速码字搜索算法是矢量量化的核心问题之一,其性能决定了编码时间。快速码字搜索算法中,绝对误差不等式删除算法(AEI)是一种典型的3步算法,其第1步查找输入矢量的初始匹配码字的方法采用了Minimax法,是整个AEI算法中计算量最大的步骤,严重影响了算法的效率。针对这个问题,提出了一种新的查找初始匹配码字的方法——Partial Minimax法。该方法在保证所找到的初始匹配码字与原始AEI算法相同并且重建图像的PSNR（峰值信噪比）值不变的前提下,可显著减小这一步骤的计算量和查找时间,从而有效地提高了算法的总体编码速度。     

等和值块扩展最近邻矢量量化码字搜索算法

论文提出一种等和值块扩展最近邻矢量量化码字搜索算法。该算法将码书按和值大小排序分块,并将每一块中间或中间附近的码字的和值作为本码书块的特征和值。编码时,查找与输入矢量和值距离最近的码书块并作为初始匹配码书块。然后在该码书块附近上下扩展搜索相邻码书块中距输入矢量最近的码字。该算法具有无复杂运算的特点,易于VLSI技术实现。仿真结果表明,该算法是一种有效的码字搜索算法。     

基于Hadamard变换和矢量分割的快速搜索算法

为了对图像信号进行快速有效压缩,提出了一种改进的基于Hadamard变换和矢量分割的双测试算法.该算法首先在Hadamard域中对空域双测试算法的两个删除准则进行了等效变换;然后在实验的基础上,对变换域码字和输入矢量进行了恰当的矢量分割;最后在码字搜索过程中,利用其中一个最为有效的删除准则来排除大部分的不匹配码字.实验结果表明,改进算法能大大提高码字的搜索效率,搜索范围可减少到原始算法搜索范围的约14%～17%.总体编码时间也减少到原始算法编码时间的约35%～45%.     

基于改进的参考矢量选取的码字快速搜索算法

矢量量化的编码过程计算复杂性极高,为了减少编码时大量的矢量间距离计算,许多文献提出利用不等式关系以较少的计算量来估算距离的方法。在Chang等人提出的利用双限制三角不等式的快速搜索算法基础上,通过改进参考矢量的选取方法,有效提高了码字搜索的效率。实验结果表明,改进算法的码字排除率可以提高3.735%9.976%,编码时间可以减少6.03%35.25%。     

最大概率匹配的矢量量化编码算法

文章提出了一种最大概率匹配的矢量量化编码算法,它为码书中的每一码字增加一个计数器,统计在编码图象时每个码字的出现的频数,并进行排序;在量化矢量时,根据当前码字出现频数大小依次选择侯选码字,即频数大的码字优先选为候选码字。该算法可以和已有的预测法结合,形成预测加最大概率匹配的联合矢量量化编码算法。实验表明,联合算法的效率较高,在最初几次的搜索中就能以较高的命中率命中最佳匹配码字。     

一种快速的矢量量化编码

研究了一种基于均方误差（MSE）测度的矢量量化快速编码算法。算法利用小波变换的特点,合理地构造矢量,便于非线性插补矢量量化技术的使用,也使部分失真排除法的效率大大提高。使用矢量的二范数和距离测度关系的码字排除方法,再结合非线性插补矢量量化技术和部分失真排除法,在搜索编码过程中,有效排除部分候选码字。实验结果表明,相对于穷尽搜索方法,计算量有明显降低,计算时间显著减少。     

快速码字搜索算法中一维特征量的最佳选择方法

矢量量化编码过程中的最近邻码字搜索需要进行大量的矢量间距离的计算,这个过程的计算复杂度极高,严重限制了其实际使用.为了加速矢量量化的编码过程,许多文献提出了各种不同组合的基于均值、2-范数、方差和角度的矢量一维特征量的快速最近邻矢量量化码字搜索算法.通过实验给出了这四个一维特征量单独使用以及相互组合的所有情况下各算法的搜索范围和编码时间,并对它们进行了比较和分析,进而提出了在实际进行编码时如何最优地进行一维特征量选取的准则.     

改进的快速相关矢量量化的图像编码算法

在矢量量化中,保证编码质量的前提下,缩短编码时间和降低码率是当前研究的重要问题。快速码字搜索算法是减少编码时间的重要技术。提出了一种改进的哈达玛变换域等均值等方差最近邻搜索算法（MHTEENNS）。测试结果表明,这种算法能够排除更多的码字,效率更高。为了降低码率和进一步缩短编码时间,目前已有相关矢量量化的图像编码算法,但是这种算法造成编码质量的下降。提出了改进的基于对角线相关矢量量化编码算法（MDFCVQ）。该算法编码质量提高了0.8~0.9 dB且码率进一步降低。最后,将快速码字搜索算法应用到相关矢量量化中来,将两种改进后的技术结合在一起,通过与之前的方法比较,提出一种在保证编码时间的前提下,具有更高编码质量和更低码率的矢量量化算法。     

改进的矢量量化码字快速搜索法

矢量量化技术是一种高效和有竞争力的数据压缩方法,但由于其编解码过程中需要较大的计算量影响了其使用。提出了一种改进的基于子矢量特征值的码字快速搜索算法。算法充分利用矢量的3个特征值即和值、子矢量和值以及方差,建立起一种5步码字排除法,使得算法能够快速排除大部分不匹配码字,实现减少计算量的目的。仿真实验结果表明,算法的计算量要小于ZhiBin算法、Pan算法以及Chen算法,证明了改进算法的有效性。     

PDVQ图像编码系统的算法研究

PDVQ图像编码系统首先将码书进行方向性分类,把每类方向性码书中的码字按码字和值进行升序排列,并根据EBNNS算法将码书分块。编码时,先根据输入图像块的相关性进行PDVQ编码,然后分析输入图像块的方向性来选择相应的分类子码书,在该子码书中根据输入图像块的和值确定码字搜索范围,最后在确定的搜索范围内搜索最匹配码字。仿真结果表明,该系统集合了动态图像块划分（PDVQ）、基于方向性分类编码和等和值块扩展最近邻码字搜索（EBNNS）三种算法的优点,在保证重建图像质量前提下,缩短了编码时间,并提高了压缩比。     

Hadamard transform based fast codeword search algorithm for high-dimensional VQ encoding

An efficient nearest neighbor codeword search algorithm for vector quantization based on the Hadamard transform is presented in this paper. Four elimination criteria are derived from two important inequalities based on three characteristic values in the Hadamard transform domain. Before the encoding process, the Hadamard transform is performed on all the codewords in the codebook and then the transformed codewords are sorted in the ascending order of their first elements. During the encoding process, firstly the Hadamard transform is applied to the input vector and its characteristic values are calculated; secondly, the codeword search is initialized with the codeword whose Hadamard-transformed first element is nearest to that of the input vector; and finally the closest codeword is found by an up-and-down search procedure using the four elimination criteria. Experimental results demonstrate that the proposed algorithm is much more efficient than the most existing nearest neighbor codeword search algorithms in the case of problems of high dimensionality.     

Fast searching algorithm for vector quantisation based on features of vector and subvector

Vector quantisation (VQ) is an efficient technique for data compression and retrieval. But its encoding requires expensive computation that greatly limits its practical use. A fast algorithm for VQ encoding on the basis of features of vectors and subvectors is presented. Making use of three characteristics of a vector: the sum, the partial sum and the partial variance, a four-step eliminating algorithm is introduced. The proposed algorithm can reject a lot of codewords, while holding the same quality of encoded images as the full search algorithm (FSA). Experimental results show that the proposed algorithm needs only a little computational complexity and distortion calculation against the FSA. Compared with the equal-average equal-variance equal-norm nearest neighbour search algorithm based on the ordered Hadamard transform, the proposed algorithm reduces the number of distortion calculations by 8 to 61%. The average number of operations of the proposed algorithm is ,79% of that of Zhibin?s method for all test images. The proposed algorithm outperforms most of existing algorithms.     

Novel full-search schemes for speeding up image coding using vector quantization

The routine for finding the closest codeword in the encoding phase of vector quantization (VQ) is high computational complexity and time consuming, especially when the codewords deal with the high-dimensional vectors. In this paper, we propose three newly developed schemes for speeding up the encoding phase of VQ. The proposed schemes can easily filter out many impossible codewords such that the search domain is reduced. The experimental results show that the computational time of our proposed schemes can save more than 41–52% computational time in a full search scheme. Furthermore, our schemes only require fewer than 84% of the computational time required in recently proposed alternative.     

A fast vector quantization encoding algorithm based on projection pyramid with Hadamard transformation

Vector quantization (VQ) for image compression requires expensive time to find the closest codevector in the encoding process. In this paper, a fast search algorithm is proposed for projection pyramid vector quantization using a lighter modified distortion with Hadamard transform of the vector. The algorithm uses projection pyramids of the vectors and codevectors after applying Hadamard transform and one elimination criterion based on deviation characteristic values in the Hadamard transform domain to eliminate unlikely codevectors. Experimental results are presented on image block data. These results confirm the effectiveness of the proposed algorithm with the same quality of the image as the full search algorithm.     

Fast Implementation of KLT-Based Speech Enhancement Using Vector Quantization

We propose a new method for implementing Karhunen–Loeve transform (KLT)-based speech enhancement to exploit vector quantization (VQ). The method is suitable for real-time processing. The proposed method consists of a VQ learning stage and a filtering stage. In the VQ learning stage, the autocorrelation vectors comprising the first$K$elements of the autocorrelation function are extracted from learning data. The autocorrelation vectors are used as codewords in the VQ codebook. Next, the KLT bases that correspond to all the codeword vectors are estimated through eigendecomposition (ED) of the empirical Toeplitz covariance matrices constructed from the codeword vectors. In the filtering stage, the autocorrelation vectors that are estimated from the input signal are compared to the codewords. The nearest one is chosen in each frame. The precomputed KLT bases corresponding to the chosen codeword are used for filtering instead of performing ED, which is computationally intensive. Speech quality evaluation using objective measures shows that the proposed method is comparable to a conventional KLT-based method that performs ED in the filtering process. Results of subjective tests also support this result. In addition, processing time is reduced to about 1/66 that of the conventional method in the case where a frame length of 120 points is used. This complexity reduction is attained after the computational cost in the learning stage and a corresponding increase in the associated memory requirement. Nevertheless, these results demonstrate that the proposed method reduces computational complexity while maintaining the speech quality of the KLT-based speech enhancement.     

TPC基于相关运算的迭代译码算法

Chase-Pyndiah算法（简称C-P算法）为Turbo乘积码（TPC）译码中常采用的算法之一。在C-P算法的基础上,引入一种基于相关运算的迭代译码算法,采用相关作为度量,可以避免复杂的欧氏距离计算;在选择候选码字时引入度量比较的方法,省去了对竞争码字的搜索;通过去除候选码字中相同元素对符号集合进行简化,降低了译码复杂度和译码延时。经算法分析与仿真表明,与已有的软判决算法相比,该算法的译码速度更快而译码性能没有降低,非常适合硬件实现。     

Accelerating VQ-based codeword search on the basis of partial search strategy

In this paper, a technique for accelerating the search on VQ-based codeword search is proposed. With our approach, all the pixel blocks of vector representation in an image picture could be encoded efficiently into their corresponding indices, and be associated with the closest codeword in the pre-generated codebook. The technique adopted in our scheme is inspired by the concept of space partition of the initial codebook. It is accomplished in a manner that the search range for the image block is significantly reduced. There is a key-codebook comprised of numerous key-codewords, and with a smaller book size, which is generated from the given codewords during system initialization. Any image block is then directed to look for the closest key-codeword in the key-codebook. Ultimately, the best-match codeword is checked out according to the relation between the closest key-codeword and the ‘genuine’ codewords in the given codebook. This short-time achievement is obtained because of the considerable book size reduction. A flexible radius, spread by a key-codeword is imposed in our elaborated algorithm to attain the most precise hit ratio estimation. The experiments show that our scheme is at least two and a half times faster than that of a full search in VQ implementation. Moreover, the strategy we proposed is also compatible with the search algorithms in finding the closest codeword, and the high quality of image display remained the same.     

An improved search algorithm for vector quantization using mean pyramid structure

Vector quantization (VQ) is a well-known data compression technique. In the codebook design phase as well as the encoding phase, given a block represented as a vector, searching the closest codeword in the codebook is a time-consuming task. Based on the mean pyramid structure and the range search approach, an improved search algorithm for VQ is presented in this paper. Conceptually, the proposed algorithm has the bandpass filter effect. Each time, using the derived formula, the search range becomes narrower due to the elimination of some portion of the previous search range. This reduces search times and improves the previous result by Lee and Chen (A fast search algorithm for vector quantization using mean pyramids of codewords. IEEE Trans. Commun. 43(2/3/4), (1995) 1697–1702). Some experimental results demonstrate the computational advantage of the proposed algorithm.     

Adaptive embedding techniques for VQ-compressed images

An embedding algorithm, which can adaptively embed a binary message into a VQ-compressed image, is proposed in this paper. The proposed algorithm is divided into three phases. In the codeword grouping phase, a new group of codewords is initiated by the two most similar codewords which do not belong to any group. For each codeword which does not belong to any group, if the codeword is similar to all of the codewords in the group, it will be added to the group. In the embedding phase, each codeword in a group will be assigned to embed a certain sub-message whose length is determined by the number of codewords in the group. The more codewords a group has, the higher the embedding capacity of a codeword in the group will be. In the extracting phase, given a codeword and the number of codewords in the group to which the codeword belongs, the embedded message can be extracted from the codeword by simply determining the order of the codeword in the group. Experimental results show that the proposed algorithm performs better than previous algorithms with regard to embedding capacity and image quality. For the test images, when the embedding capacity is less than 5 bits per codeword index, the difference of the PSNR values between the stego-image and its VQ-compressed cover image will be no more than 5 dB on average.