在數位影像處理領域中，影像去雜訊是眾多重要的主題之一。在近些年來數位相機上感應器的製造技術已經大幅地進步了，但是在擷取影像時或多或少還是會受到雜訊的干擾。因此影像去雜訊演算法總是迫切需要的且吸引眾多研究人員試著去尋找出更好的解決方法。目前為止，已經有許多去除雜訊的演算法被提出了，像是平均濾波器或是中值濾波器。每個濾波器都有不錯的表現，但是無時無刻還是有很多更好的演算法被發表，而在眾多現有的演算法中，西格瑪濾波器有著低複雜度以及不錯的效能。
　　本論文提出一個新的去雜訊演算法，此演算法將受到雜訊干擾的影像分解成兩個部份，並將此兩部份分別利用適應性西格瑪濾波器去除雜訊。在論文的最後會將我們的演算法與其它現有的演算法做比較，經實驗結果證明我們的演算法在時間複雜度及效能方面都有卓越的表現。

Image noise removal is one of the most important subjects in digital image processing field. Although the manufacturing technology of the digital camera sensor is advanced with each passing day, it is inevitable that pictures are interfered with noise more or less when capturing pictures. Therefore, image noise removal algorithm is always an urgent demand and attracts the attention of many researchers to seek out the best solution all the time. So far there has been several image noise removal algorithm that have been proposed such like ’Mean Filter’, ’Median Filter’...etc. All show an outstanding performance, but it remains that there are many better algorithms proposed all the time. Among various existing algorithms, the sigma filter represents low complexity and good filtering performance.In this thesis, a new algorithm that first decomposes the input image into
two components that are independently processed using a standard sigma filter is proposed. Then, ourput image is reconstructed from the filtered components. Finally, some experiments comparing the proposed method with some existed noise removal methods are presented. Experimental results show that the proposed method has better performance and efficiency compared to other compared algorithms.

[1] L. Alparone, S. Baronti, and A. Garzelli. A hybrid sigma filter for unbiased
and edge-preserving speckle reduction. International Geoscience
and Remote Sensing Symposium, 2:1409–1411, 1995.
[2] F. Torkamani Azar and K. E. Tait. Image recovery using the anisotropic
diffusion equation. Digital Object Identifier, 5:1573–1578, 1996.
[3] Radu Ciprian Bilcu and Markku Vehvilainen. A new image de-noising
technique based on image decomposition and sigma filtering. WSEAS
Transactions on Communications, 4:579–586, August 2005.
[4] S. A. G. Chang, B. Yu, and M. Vetterli. Adaptive wavelet thresholding
for image denoising and compression. IEEE Trans. Image Processing,
9:1532–1546, 2000.
[5] Michael Elad. On the origin of the bilateral filter and ways to improve
it. IEEE Transactions on image processing, 11:1141–1151, 2002.
[6] G. Fan and X. G. Xia. Image denoising using local contextual hidden
marcov model in the wavelet domain. IEEE Signal Processing Letters,
8:125–128, 2001.
[7] Rafael C. Gonzalez and Richard E. Woods Woods. Digital Image Processing.
Robbins, Tom, second edition edition, 2002.
[8] Marian Kazubek. Wavelet domain image denoising by thresholding and
wiener filtering. IEEE Signal Processing Letters, 10:324–326, 2003.
[9] Chi-Kin Lam. The bootstrap mean filter for image restoration. Conference
on Signals, Systems and Computers, 1:578–582, 1993.
[10] Jong-Sen Lee. Digial image smoothing and the sigma filter. Computer
Vision, Graphics, and Imagge Processing, 24:255–269, 1983.
[11] M. Lindenbaum, M. Fischer, and A. M. Bruckstein. On gabor contribution
to image-enhancement. Patern Recongnition, 27:1–8, 1994.
[12] IOANNIS PITAS. Nonlinear mean filters in image processing. IEEE
Transactions on Acoustics, Speech, and Signal Processing, 34:573–584,
1986.
[13] P.Perona and J. Malik. Scale space and edge detection using anisotropic
diffusion. IEEE Trans. Patt. Anal. Mach. Intell., 12:629–639, 1990.
[14] Dong-Hyuk Shin, Rae-Hong Park, Seungjoon Yang, and Jae-Han Jung.
Block-based noise estimation using adaptive gaussian filtering. IEEE
Transactions on Consumer Electronics, 51:218–226, 2005.
[15] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images.
Proceedings of International Conference on Computer Vision,
pages 839–846, 1998.