The restoration of X-ray radiograph based on ICA

Abstract In the system of X-ray radiograph, the scattered X-ray induces the depression and degradation of the image quality, and badly influences the detecting sensitivity. After studying mechanism of image degradation, and analyzing the scattering polarization, a new restoration method based on the blind separation and wavelet transform was raised. An ICA (Independent Component Analysis) model was firstly constituted based on the radiograph mechanism. To satisfy to the statistically independence of blind separation, the sub-band images by wavelet transform were utilized as estimating source. We utilized the least mutual information entropy as the criteria for blind separation and deduced to the optimization estimation. The experimental results show that the method can effectively depress the scattering and improve the contrast.