基于自适应小波阈值和双边滤波器的去噪算法

Denoising Algorithm Based on Adaptive Wavelet Threshold and Bilateral Filter

针对以往小波阈值去噪算法在去噪过程中出现的去噪不彻底、噪声误判和图像边缘模糊的问题,提出了一种新的基于自适应小波阈值和双边滤波器的图像去噪算法。该算法中的小波阈值随着分解尺度和子带的变化而变化,这样不同分解尺度和不同子带采用不同的阈值进行去噪,克服了统一阈值的不足,增强了算法的自适应性;在软阈值函数去噪之后,利用双边滤波器达到保护图像边缘的目的。仿真实验表明,该算法能够有效地去除图像噪声,改善图像的视觉质量,并且能够较好地保留图像的边缘和细节信息。

A novel image denoising algorithm based on an adaptive wavelet threshold and the bilateral filter was proposed in view of the drawbacks of traditional wavelet threshold algorithm for image noise reduction that it could not eliminate the noise thoroughly, and might remove the useful information and blur the image edge. The algorithm selected an adaptive wavelet threshold dependent on the change of the decomposition scale and the subband, so that different thresholds in different decomposition scales and different subbands for eliminating the noise overcame the lack of the universal threshold and enhanced the adaptability of the algorithm. In order to preserve the image edge, a bilateral filter was used after the wavelet soft threshold function denoising. Simulation results show that this algorithm not only eliminates the noise effectively and improves the visual quality of the image, but also better preserves important image features, such as the edges and detail information.