CT Image De-noising Model Based on Independent Component Analysis and Curvelet Transform

Abstract

CT image De-noising is an important research topic both in image processing and biomedical engineering. Independent component analysis (ICA) is a statistical technique where the goal is to represent a set of random variables as a linear transformation of statistically independent component variables. The curvelet transform as a multiscale transform has directional parameters occurs at all scales, locations, and orientations. This paper proposes a new model for CT medical image de-noising, which is using independent component analysis and curvelet transform. Firstly, a random matrix was produce to separate the CT image into a separated image for estimate. Then curvelet transform was applied to optimize the coefficients. At last, the coefficients were selected for image reconstruction by inverse of the curvelet transform. By contrast, this approach could remove more noises and reserve more details, and the efficiency of our approach is better than other traditional de-noising approaches.