摘要
在D.L.Donoho和I.M.Johnstone提出的小波阈值滤波法的基础上,提出了一种基于二进小波变换的图像阈值滤波法。在阈值函数中引入参数,通过调整参数以获得最佳的小波系数的阈值估计,使得改进阈值介于硬阈值与软阈值之间。为分析此方法的去噪性能,对同一图像在叠加不同水平的Gaussian噪声的情况进行了去噪实验,仿真实验结果发现基于二进小波变换的图像阈值滤波法不但有效抑制了图像边缘附近的Gibbs现象,而且使去噪后图像的峰值信噪比在不同噪声水平下都有很大程度地改善,在不同噪声水平间有很小幅度的波动,这表明基于二进小波变换的图像阈值滤波法的去噪性能具有很强的稳定性。
A threshold de--noising method based on dyadic wavelet transform was proposed here based on the wavelet shrinkage put for word by D. L. Donoho and I. M. Johnstone. A parameter can be adjusted properly in the new threshold function to obtain the best estimations of the wavelet coefficients which ena- bles this function to become a more general case incorporating the hard and soft threshold. To analyze the image de--noising performance of this method, de--noising experiments was conducted on the same image in different levels of Gaussian noise. The simulation results showed that the image threshold de--noising method based on dyadic wavelet transform not only suppressed the Gibbs phenomenon near the edge of the image effectively, but also it made the peak signal to noise ratio of the de--noising images have a large ex- tent improved at different noise levels, and have a very small range of fluctuation in different noise levels, which results indicate that de--noising performance of the image threshold de--noising method based on dyadic wavelet transform has a strong stability.
出处
《新疆师范大学学报（自然科学版）》
2013年第2期1-6,共6页
Journal of Xinjiang Normal University(Natural Sciences Edition)
基金
国家自然科学基金资助项目(11261061
10661010)
新疆维吾尔自治区自然科学基金项目(200721104)
关键词
二进小波变换
图像去噪
噪声水平
性能分析
Dyadic wavelet transform
Lmage de--noising
Noise level
Performance analysis
