使用不同频率域残差和K-SVD模型的图像消噪方法

Image denoising method by using different frequency domain residuals and K-SVD model

图像消噪前后的残差信息包含图像的高频信息.为了提高消噪图像的质量,在轮廓波变换域内,根据噪声图像及其K-SVD消噪后不同频率子带图像的残差信息,对残差子图像块再次进行K-SVD消噪,并将其结果与消噪图像的子带图像进行融合,得到包含残差信息的消噪子带图像,最后通过轮廓波逆变换得到消噪图像.仿真实验结果证明了所提出的基于不同频率子带内残差信息和K-SVD的图像消噪方法优于轮廓波变换和K-SVD模型,具有较好的消噪性能.

The residual information before and after image denoising includes the high frequency information of the image. In order to improve the quality of the image denoised and according to the residual information of noise image and its sub-band images denoised by K-SVD at different frequencies, K-SVD denoising is performed on the residual sub-images again, and the result is fused with the sub-band images of the image denoised to obtain the sub-band images denoised containing residual information. Finally, the image denoised is obtained by the inverse contour wave transform. The simulation results show that the proposed image denoising method based on in-band residual information of different frequencies and K-SVD is superior to the contour wave transform and K-SVD model and has better denoising performance.