Novel vector quantization inceptive code book generating method

Abstract

The invention relates to a new generation method of initial codebook of quantization of vector, which pertains to the technology field of the process of digital images and digital audio. The beginning is the initialization of parameter, and the following process is a circulation process: first, calculating distance threshold; writing a first cluster exercising vector into a cluster vector group, and then calculating a second exercising vector and its distance d1; If the distance d1 is bigger than d0, putting the second exercising vector into the cluster vector group; if not, including the second exercising vector in the cell of the first cluster vector and calculating the vector number of the cell; second, calculating sizplus; third, judging, if at this time the number of vectors of the codebook is siz book, requirement is meet and the calculation finishes; if the codebook increment brought by circulation plus the current codebook size can not meet the codebook size set by design mark, deleting all the vectors in each marked cell collectively from the exercising vectors and switching to the first step.

Description

technical field [0001] The invention belongs to the technical field of digital image and digital audio processing, and in particular relates to a new method for generating an initial codebook for vector quantization. Background technique [0002] Vector quantization technology is widely used in the compression of digital images and digital audio. In the process of vector quantization of digital images, the image is divided into 4×4 small blocks to form a 16-dimensional vector for vector quantization; while in digital audio compression, every n (such as 16) line spectrum frequencies (LSF) Construct an n-dimensional vector for vector quantization [0003] In vector quantization, the design of the codebook plays a key role. Classic codebook design methods include LBG algorithm, neural network-based codebook design methods (such as self-organizing feature map neural network codebook design SOFM), simulated annealing codebook design algorithm (simulated annealing, SA), and so o...

AI Technical Summary

Problems solved by technology

A disadvantage of the random extraction method of the training vector set is that some atypical vectors may be selected as code vectors, resulting in only a few vectors in the cell, or even only one initial code vector, and these atypical vectors are retained in each iteration or centroids of atypical vectors; another disadvantage is that some spaces are too finely divided and others are too coarsely divided

These two shortcomings will cause some code vectors in the codebook to be underutilized, which will affect the performance of the codebook and the convergence speed of the subsequent LBG algorithm.

Images