The Application of Independent Component Analysis in CT Image De-Noising

摘要

The diagnosis rate depends on the image quality, and the CT image with superior quality is the precondition of accurate diagnosis. Through analyzing the deficiency of many existing methods on de-noising, we put forward an application of independence composition analysis (ICA) method to remove the noise from a CT image. Experimental results indicate that, compared with the other methods, the proposed method has a better performance in eliminating the noises with Gauss and salt and pepper, which are superimposed on CT images.