摘要
提出了一种基于混合蚁群算法的矢量量化码书设计算法。该算法首先通过自适应地调整截取转移概率的参数,加大蚁群算法的搜索最优解的力度;然后以蚁群算法搜索的结果作为初始解,利用改进的LBG算法作进一步的搜索,从而加快算法的收敛速度。实验结果表明,该算法不但大大提高码书性能,而且也缩短了运行时间,解码恢复图像能获得较高的主、客观质量。
An appropriately adapted ant colony system embedded with a simple improved LBG algorithm was proposed for vector quantization codebook design. This algorithm first enhances the optimal solution search capability of ant colony algorithm through the adaptive adjustment of the intercept parameter of the transition probability, and then makes use of the searched results of ant colony algorithm as initial solutions, and use improved LBG algorithm for further search, thus accelerate the convergence of the algorithm. Experimental results show that the new algorithm not only further improve the coding performance, but also decrease the running time.
出处
《通信学报》
EI
CSCD
北大核心
2005年第9期135-139,共5页
Journal on Communications
基金
国家自然科学基金资助项目(60372087)
关键词
图像压缩
蚁群算法
矢量量化
码书设计
image compression
ant colony algorithm
vector quantization
codebook design
