基于PCA和BM3D的噪声估计方法及其在中子图像去噪中的应用

Noise Level Estimation Method Based on PCA and BM3D for Neutron Image Denoising

针对中子图像的去噪问题,本文提出了一种弱化残差图像特征值的噪声估计方法。该方法将残差图像作为噪声图像,利用主成分分析(PCA)分析了残差图像特征值,估计了噪声强度。根据噪声强度,应用三维块匹配方法(BM3D)去除了噪声,逐步弱化残差图像特征值,得到了最终噪声估计值。实验结果表明,该方法能估计模拟噪声图像和实际含噪中子图像的高斯噪声,计算效率高,可实现较好的去噪复原效果。

To solve the problem of neutron image denoising,a noise level estimation method of weakening residual image eigenvalue was proposed.In this method,the principal component analysis(PCA)was utilized to analyze residual image eigenvalue and the noise level was estimated.According to the noise level,the image was denoised,and the residual image eigenvalue was weakened to acquire the final estimated noise level.The experimental results show that the proposed method can estimate the Gaussian noise level of the simulated image and the real neutron image,and achieve preferable denoising effect with high computational efficiency.