论文部分内容阅读
根据图像小波分解的特点和小波分解后高频小波系数的统计特性,构造了一种新阈值函数的去噪算法。与传统的硬阈值、软阈值函数相比,新阈值函数考虑了图像能量分布的特点,对于每一小波系数乘以一个与自身大小相关的降噪因子,并且新阈值函数简单易于计算,具有较强的自适应性。实验结果表明,采用新阈值函数的去噪结果能够有效地抑制图像的马赛克效应,无论在视觉效果上,还是在信噪比增益上均优于传统的软、硬阈值方法。
According to the characteristics of image wavelet decomposition and the statistical characteristics of high frequency wavelet coefficients after wavelet decomposition, a new threshold function denoising algorithm is constructed. Compared with the traditional hard threshold and soft threshold functions, the new threshold function takes into account the characteristics of the image energy distribution. For each wavelet coefficient multiplied by a noise factor related to its own size, and the new threshold function is simple and easy to calculate, Strong adaptability. The experimental results show that using the new threshold function can effectively suppress the mosaic effect, which is superior to the traditional soft and hard threshold methods both in visual effect and signal-to-noise ratio.