Ultrasound Image Restoration Using Spatially Adatpive Filter for Indepdent Components Analysis

A novel image restoration method for ultrasound images is proposed. The method is based on independent component analysis (ICA). We assume that speckle noise comes from a signal source, which accompanies but is independent of the "true signal source" and their statistical characteristics are not the same. Thus the image restoration problem can also be described as "signal source separation and enhancement" problem. Then we classify the basis images that span into two different subspaces, namely "true signal subspace" and "speckle subspace". Based on the classification result, we build our spatially adaptive filter and obtain the recovered image after a mixing transform. The experimental results show that the proposed method achieves a better performance improvement as compared to other methods for laser ultrasound images of structured objects blurred by speckle noises