摘要
利用小波变换的自适应特征,将小波的多分辨理论应用于图像的去噪、增强处理中,针对传统的阈值去噪和子带增强的缺点,提出了一种改进的自适应图像去噪增强算法。该算法对图像的噪音进行了估计,采用软阈值和硬阈值相结合的处理方法,利用3次B样条插值函数的特性,设计一个平滑的过渡区,有效地避免了单独使用软阈值或硬阈值处理的缺点,保证了图像达到比较好的去噪效果;同时引入的增益因子,可以自适应地补充图像的弱信息。
Based on the adaptive character of wavelet transform, wavelet multiresolution theory is used to the process of image enhancement and de-noise. In order to overcome the shortcomings of threshold de-noise and enhance the band of frequency, an improved algorithm for image self-(adaptive) enhancement and de-noise was proposed. In this algorithm, the estimating of the (image′s) noise is accurate; the image′s de-noise effect is great by using tri-B-spline interpolation function to design a smooth transition area, and also it can effectively avoid the disadvantage using soft threshold or hard threshold respectively; at the same time, the image′s weak information is supplemented adaptively by adding the plus factor.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2005年第2期298-301,共4页
Journal of Central South University:Science and Technology
关键词
小波变换
傅里叶变换
自适应增益
B样条插值函数
wavelet transform
Fourier transform
adaptive enhancing
B-spline interpolation function
