期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2012
卷号：9
期号：4
出版社：IJCSI Press
摘要：The diagnosing of disease using speckled ultrasound image is a very difficult task for doctors. The speckle noise not only hinders the visual information but also affect the segmentation process used in ultrasound image processing. Thus speckle noise suppression is necessary pre-processing task in order to maintain the diagnostic potential of ultrasound imaging. This paper proposes an efficient technique for speckle noise removal. The proposed technique is implemented using Bacterial Foraging Optimization (BFO) cascaded with Wiener-Helstrom filter. Wiener-Helstrom filter processes the ultrasound image by making the filtering less sensitive to slight changes in input conditions. BFO algorithm used as an optimization technique to minimize the error between the noisy image and the Wiener-Helstrom filter output image. The error percentage of 0.0001 is maintained here. It has been observed by the experimental results that the proposed method outperform and gives superior result to conventional methods. The efficiency is measured in the form of Peak Signal to Noise Ratio(PSNR), Mean Square Error(MSE) and Mean Absolute Error(MAE) and Signal to Mean Square error(S/MSE).
关键词：Speckle noise; Wiener;Helstrom filter; BFO; PSNR; MSE; MAE S/MSE
