改进模拟退火算法在矢量量化编码中的应用  

An Improved Simulated Annealing Algorithm and Its Application in Vector Quantization Coding

作　　者：刘燕[1] 郭英[1] 

机构地区：[1]空军工程大学电讯工程学院,陕西西安710077

出　　处：《通信技术》2008年第2期81-82,88,共3页Communications Technology

基　　金：国家自然科学基金项目(60601016);陕西省自然科学基金项目(2006F40)

摘　　要：为了提高模拟退火算法的最终解的质量,文中对控制算法进程的冷却进度表进行了优化选取,尤其在控制马尔可夫链长方面,给出了依据算法搜索过程的反馈信息来控制马尔可夫链长的方法。将该算法与LBG算法相结合,应用于矢量量化图像编码,既保持了模拟退火对初始码书依赖性小、不容易陷入局部极值的优点,又具备LBG算法的易于实现和计算量小的特点。仿真实验表明,该算法提高了码书的编码性能。The cooling schedule which controls the process of Simulated Annealing is optimized. In particalar, according to the feedback information of search course of Simulated Annealing, a method for controlling the length of Markov Chain is determined. The proposed method is applied to the vector quantization image coding, which is not very dependence on initial codebook, and not easy to fall into local minimization, with features of LBG algorithm in easy implementation, simple calculation. Simulation results show that this method can effectively improve the performance of the codebook.

关 键 词：模拟退火 冷却进度表 马尔可夫链 矢量量化 图像压缩 

分 类 号：TN912.3[电子电信—通信与信息系统]