期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：7
出版社：S.S. Mishra
摘要：The need for good image quality for an accurate and efficient diagnosis has become a necessity. To ensure good image quality, denoising has become a mandatory step. Magnetic Resonance (MR) images are corrupted by noise due to inhomogenuity of magnetic field, excursion of temperature, motion of the tissue, etc. Speckle noise is a type of granular noise which degrades the quality of the image with the appearance of backscattered wave. This paper aims at providing a performance comparison of different denoising techniques for the removal of speckle noise in MR images. The performance comparison was done by using parameters such as Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Mean Structural Similarity (MSSIM), etc. The variation of MSE with respect to increase in noise variance for different noise removal techniques is also covered in this paper
