摘要
在经典的空间几何线性均值收缩算法的基础上，提出了一种非线性空间几何收缩算法。由实验表明，该算法不仅能提高压缩比，而且对信噪比也有一定的改善。
Based on the analysis of neural network competitive learning algorithms and fuzzy C means algorithms, two new fuzzy competitive learning algorithms (FCL1 and FCL2) have been proposed, and the fuzzy membership functions have been investigated. Both the theoretical analysis and the experimental results have proven that the proposed fuzzy competitive learning algorithms are efficient for image vector quantization compression coding.
出处
《中国图象图形学报（A辑）》
CSCD
1997年第7期491-492,共2页
Journal of Image and Graphics
基金
机械工业部跨世纪人才基金
关键词
分形
分形图象压缩
迭代函数系统
编码
非线性
Image compression, Fuzzy competitive learning, Vector quantization, Neural network
