A direct restoration method for spectral and image analysis
暂无分享,去创建一个
Physical constraints to directly control the output restoration are introduced in each iteration of solving the spectral or image formation equation. For the purpose of increasing the restoration sensitivity and the capability of smoothing noises, the fitting technique is used to reform the resolved equation. Our reconstruction results for Monte Carlo samples and observation data from space high energy astronomy show that, in comparison with traditional restorations, the direct method has high sensitivity, high resolution ability and capability of effectively reducing the effect of statistical fluctuation in data and can be used in the case of poor statistics. This method is model independent and has the capability to simultaneously represent both the extended and discrete features in object.
[1] Carl Erik Fröberg,et al. Introduction to Numerical Analysis , 1969 .
[2] B. Efron. Bootstrap Methods: Another Look at the Jackknife , 1979 .
[3] Charles R. Johnson,et al. Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.
[4] S. Gull,et al. Image reconstruction from incomplete and noisy data , 1978, Nature.
[5] John Skilling,et al. Maximum Entropy and Bayesian Methods in Applied Statistics: The Cambridge Maximum Entropy Algorithm , 1986 .