Speckle noise reduction based on least squares approximation

Edge-preserving noise reduction is an essential operation for computer-aided ultrasound image processing and understanding. This paper describes a novel method for reducing speckle noises in ultrasound images, which is based on least squares fitting a two-dimensional polynomial function to underlying image intensities. The performances of the proposed noise reduction method have been compared with those of the commonly used median filter in eliminating speckle noises in ultrasound thyroid images. Experimental results indicate that the proposed method can achieve the same good level of noise reduction and edge preservation as those of median filters, but with far less computation time