论文信息 - A statistical model for complex images: bivariate gaussian MRF - BGMRF

A statistical model for complex images: bivariate gaussian MRF - BGMRF

In this paper we present a new Gaussian MRF model for complex images. This model is defined starting from a Gaussian MRF, generalizing it for complex images, and imposing a covariance matrix expression which considers a correlation between the real and imaginary part of the image. The hyperparameter’s estimation problem and application to linear microwave tomography are both addressed.

[1] Vito Pascazio,et al. Statistical regularization in linearized microwave imaging through MRF-based MAP estimation: hyperparameter estimation and image computation , 2003, IEEE Trans. Image Process..

[2] V. Pascazio,et al. Unsupervised Bayesian reconstruction of microwave images from real data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[3] Donald B. Rubin,et al. Max-imum Likelihood from Incomplete Data , 1972 .

[4] Vito Pascazio,et al. A nonlinear estimation method in tomographic imaging , 1997, IEEE Trans. Geosci. Remote. Sens..

[5] Stan Z. Li,et al. Markov Random Field Modeling in Computer Vision , 1995, Computer Science Workbench.

[6] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[7] Donald Geman,et al. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[8] Sailes K. Sengijpta. Fundamentals of Statistical Signal Processing: Estimation Theory , 1995 .