论文部分内容阅读
目前绝大多数的图像去噪算法只通过单纯处理原始噪声图本身来实现,并没有考虑将原始噪声图和去噪图相结合来进一步提升去噪性能.针对该问题,我们提出一种渐进式图像去噪算法框架.该框架基于目前去噪效果最为显著的三维块匹配算法,采用三层两次融合的设计结构,每层均采用三维块匹配算法,且每层在之前去噪基础上通过进一步融合再次去噪.充分的统计实验结果表明,在同样噪声条件下,我们的方法和另外一个最新改进算法在峰值信噪比方面相对于原始三维块匹配算法都有不同程度地提升,并且新提出的算法较传统三维块匹配算法有更好的去噪性能;随噪声程度的加大,算法性能提高的幅度愈加明显,在改善CT成像质量方面获得较好的成像效果.“,”Currently almost all denoising algorithms are implemented by processing original noisy image itself simply,which could not enhance the performance further by combining original noisy image with the denoised image.To solve the problem,a framework of progressive image denoising method was proposed.The framework is based on the block matching and 3D collaborative filtering (BM3D) algorithm,which has the most remarkable denoising effect.It includes three layers and two fusions.Each layer is implemented by BM3D and denoises the fused image generated from the previous layers.Adequate statistical results show that under the same noise condition,our proposed method and another new algorithm can improve original BM3D on PSNR to different degrees,but ours has a better performance.As the noise increases,the performance improvement is more remarkable,which means that the proposed method can improve CT imaging quality and obtain good results.