一种改进的等范数最近邻码本矢量搜索算法

An improved equal-norm nearest neighbor codeword search algorithm for vector quantization

文章提出了一种改进的等范数最近邻码本矢量搜索算法,该算法预先离线计算好各码本矢量的2-范数和它与中心线的矢量夹角,再根据各码本矢量的2-范数进行升序排列.编码时用二分法搜索到与目标矢量2-范数最近的码本矢量,再排除那些不在目标矢量形成的夹角范围内的码本矢量。结果证明,该算法对比文中列举的其他算法更加高效。

An improved codeword searching algorithm is proposed on the basis of the equal-norm nearest neighbor search algorithm. The norm and the angle made with the center line by the vector of the codeword are computed for each codeword off-line firstly, then the codewords are,ordered according to the ascending order of their norm. During the encoding process, the algorithm first selects the codeword that has the minimum norm distance from the input vector as the tentative matching codeword, and then removes the codeword which does not fall into the angle region formed by the input vector. Experimental results show that this algorithm is more efficient than other common algorithms.