摘要
提出一种基于负熵的分数低阶独立分量分析(ICA)算法,为使算法更好的适用于实际环境,结合当下较为新颖的Volterra滤波方法——VLMS算法,该算法对高斯噪声有良好的去除效果.仿真结果表明,算法对于含有两种噪声的混合图像具有良好的分离特性及实际意义.
A fractional lower order is proposed based on negative entropy of ICA method. In order to make the algorithm better suited to the actual conditions, the filtering method of VLMS is combined with good removal effect on gaussian noise. Theoretical analysis and computer simulation results show that the new method performs superior to traditional image denoising methods in removing mixed noice and practical significance.
出处
《大连交通大学学报》
CAS
2015年第3期77-81,共5页
Journal of Dalian Jiaotong University
基金
国家自然科学基金资助项目(61201419)
关键词
脉冲噪声
分数低阶
ICA
VLMS
图像去噪
random-valued impulse noise
fractional lower order
ICA
VLMS
image denoising
