Block matching based 3D filtering methods have achieved great success in image denoising tasks. However the manually set filtering operation could not well describe a good model to transform noisy images to clean imag...Block matching based 3D filtering methods have achieved great success in image denoising tasks. However the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network （CNN） for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model （BMCNN） could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio （PSNR） when denoising images with high noise levels （σ 〉 40）, and the best visual quality when denoising images with all the tested noise levels.展开更多
The principle and performance of Synthetic Impulse and Antenna Radar(SIAR) are analyzed with the concept of 3D matched filtering. The discussion here is concentrated on the characteristics of SIAR in the case of three...The principle and performance of Synthetic Impulse and Antenna Radar(SIAR) are analyzed with the concept of 3D matched filtering. The discussion here is concentrated on the characteristics of SIAR in the case of three dimensions. The results obtained are helpful for designing this new style radar.展开更多
针对低剂量CT图像质量退化问题,提出了一种基于投影域数据恢复的低剂量CT优质重建方法。新方法首先通过非线性Anscombe变换将满足Poisson分布的投影域数据转化Gaussian型分布,然后利用针对Anscombe变换的Gaussian型数据进行自适应Block-...针对低剂量CT图像质量退化问题,提出了一种基于投影域数据恢复的低剂量CT优质重建方法。新方法首先通过非线性Anscombe变换将满足Poisson分布的投影域数据转化Gaussian型分布,然后利用针对Anscombe变换的Gaussian型数据进行自适应Block-Matchingand 3D filtering(BM3D)滤波,最后通过对Anscombe逆变换数据执行传统的滤波反投影(Filtered Back Projec-tion,FBP)CT重建。由于Anscombe变换数据的方差已知,且所用BM3D滤波无需人工设置滤波参数,使得方法可实现自适应低剂量CT图像重建。仿真和临床低剂量CT数据的实验表明,方法具有良好的重建鲁棒性,其重建图像的噪声和伪影可同时得到有效抑制。展开更多
基金This research was supported by the National Natural Science Foundation of China under Grant Nos. 61573380 and 61672542, and Fundamental Research Funds for the Central Universities of China under Grant No. 2016zzts055.
文摘Block matching based 3D filtering methods have achieved great success in image denoising tasks. However the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network （CNN） for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model （BMCNN） could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio （PSNR） when denoising images with high noise levels （σ 〉 40）, and the best visual quality when denoising images with all the tested noise levels.
文摘The principle and performance of Synthetic Impulse and Antenna Radar(SIAR) are analyzed with the concept of 3D matched filtering. The discussion here is concentrated on the characteristics of SIAR in the case of three dimensions. The results obtained are helpful for designing this new style radar.
文摘针对低剂量CT图像质量退化问题,提出了一种基于投影域数据恢复的低剂量CT优质重建方法。新方法首先通过非线性Anscombe变换将满足Poisson分布的投影域数据转化Gaussian型分布,然后利用针对Anscombe变换的Gaussian型数据进行自适应Block-Matchingand 3D filtering(BM3D)滤波,最后通过对Anscombe逆变换数据执行传统的滤波反投影(Filtered Back Projec-tion,FBP)CT重建。由于Anscombe变换数据的方差已知,且所用BM3D滤波无需人工设置滤波参数,使得方法可实现自适应低剂量CT图像重建。仿真和临床低剂量CT数据的实验表明,方法具有良好的重建鲁棒性,其重建图像的噪声和伪影可同时得到有效抑制。
