雜訊消除是為影像濾波的一種實現，其分類為影像的前級處理，相關的研究眾多，近年來對於雜訊消除的方式偏向於使用模糊邏輯設計自適應(Adaptive)的雜訊濾波器，自適應性濾波器的雜訊消除方式，能夠針對不同位置的雜訊像素點運算出符合的復原值進而取代之以復原圖像，相較於非自適應性的雜訊濾波器有更佳的細節保留度與較小的影像失真。

本論文提出一個針對自適應性濾波器的改良方法，使用每張圖像中每個構圖部分都有關連性及像素強度(intensity)相似度的特性，於每個不同位置的雜訊點計算出不同但契合該像素點位置的像素復原值，其方法即在於使用了邊界的觀念，因為數位影像是使用二維座標的空間表示法，在此空間中所有像素點皆有相鄰的周圍像素點，因此在使用遮罩視窗(mask window)進行空間域濾波時，此遮罩視窗所涵蓋的範圍皆是相鄰且像素值相似像素點，因此即可利用此一特性找出此視窗所涵蓋像素值的上下邊界。

利用此上下邊界即可判斷目標點像素值是否落在此上下邊界中，若否則進入雜訊抹除的階段，於雜訊抹除階段使用模糊邏輯結合上下邊界值計算出符合的復原值，由實驗結果顯示此方法不僅可有效偵測並抹除雜訊，在影像細節與邊界的保留上也有相當好的成效。

Noise elimination is a realization of image filter. Recent research has focused on applying fuzzy theory to form an adaptive noise filter that enables to calculate an suitable value to replace a noised pixel located in anywhere of an image. By doing this way, more detailed image information can be preserved resulting in less image distortion than non-adaptive noise filter.

An improved fuzzy logical adaptive filter is proposed in this paper. Because of the characteristic of intensity similarity existing in every portion (neighborhood) of an image, all noise-free pixels can be found out by using a single mask window and its associated threshold value against a detecting area. After sorting out all these noise-free pixels, the minimum and maximum values of the sorting result respectively become lower and upper boundary to detect if a pixel value is noise or not. In the stage of noise eliminating, two masks are used to find boundaries to calculate the appropriate values for replacing noisy pixels. The usage of 2 mask windows can overcome the shortage of using single mask window that requires to assign different threshold values for different images.

By using the above-mentioned boundaries on noise detection, a target pixel can be detected as a noise or not. To eliminate noise, the fuzzy logic is incorporated to provide more tolerability on noise detection and to calculate more suitable replaced values for detected noisy pixels based on the boundary values obtained by the 2 mask windows approach. The experimental result shows that the proposed approach can not only detect and eliminate noise effectively but also well preserve image details.

[1]. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Third Edition.Pearson Education, Upper Saddle River, New Jersey 2007

[2]. 鍾國亮，影像處理與電腦視覺第五版，東華書局，台北，民國101年

[3]. 劉震昌，「數位影像處理」，高立圖數有限公司，台北，民國99年

[4]. 李啟明，應用模糊切換濾波器技術於影像脈衝式雜訊去除之研究，國立東華大學，電機工程學系，碩士論文，2005

[5]. S. J. Ko and Y. H. Lee, “Center weighted median filters and their applications to image enhancement,” IEEE Transactions on Circuits and Systems, vol. 38, pp. 984-933, 1991.

[6]. T. C. , K. K. , and L. H. Chen “Tri-State median filter for image denoising,” IEEE Transaction on Image Processing, vol. 8, No. 12. Pp. 1834-1838, 1999.

[7]. H. K. Kwan, “Fuzzy filters for noisy image filtering,” ISCAS 03.Proceedings of the International Symposium on Circuits and System, vol. 4, pp. 161-164, 2003

[8]. E. Abreu and S. K. Mitra, “ A signal-dependent rank ordered mean(SD-ROM) filter,” Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP-95, Detroit, pp. 2371-2374, 1995

[9]. 陳宏麟，結合模糊理論與中值濾波器的影像脈衝雜訊濾波器，國立台灣科技大學，電機工程研究所，2013.

[10]. T. Chen and H. R. Wu, “Adaptive impulse detection using center-weight median filter,” IEEE Signal Proceeding Letters, vol. 8, no1, Jan. 2001.

[11]. N. I. petrović and V. Crnojević, “Universal impulse noise filter based on genetic programming,” IEEE Trans. Image Process., vol. 17, no. 7, pp. 1109-1120, July 2008

[12]. Toh, K.K.V.; Isa, N.A.M., "Cluster-based adaptive fuzzy switching median filter for universal impulse noise reduction," Consumer Electronics, IEEE Transactions on , vol.56, no.4, pp.2560,2568, November 2010

[13]. Toh, K.K.V.; Isa, N.AM., "Noise Adaptive Fuzzy Switching Median Filter for Salt-and-Pepper Noise Reduction," Signal Processing Letters, IEEE , vol.17, no.3, pp.281,284, March 2010

[14]. Pei-Eng Ng; Kai-Kuang Ma, "A switching median filter with boundary discriminative noise detection for extremely corrupted images," Image Processing, IEEE Transactions on , vol.15, no.6, pp.1506,1516, June 2006

[15]. V. Thirilogasundari, V. Suresh babu, S. Agatha Janet, "Fuzzy Based Salt and Pepper Noise Removal Using Adaptive Switching Median Filter, " Procedia Engineering, Volume 38, Page 2858-2865, 2012

[16]. Y. Dong, R. H. Chan, and S. Xu, “A detetion staticstic for random-valued impulse noise, “IEEE Trans. Image Process., vol. 16, no. 4, pp. 1112-1120, Apr.2007

[17]. A. Fabijanska and D. Sankowski, "Noise Adaptive Switching median-based filter for impulse noise removal from extremely corrupted images", IET image processing, pp.472-480 July 2010.

[18]. P. Civicioglu, "Removal of random-valued impulse noise from corrupted images, " IEEE Transactions on Consumer Electronics, Vol. 55, pp. 2097-2104, Nov 2009.

[19]. J. Zhang, "An efficient median filter based method for removing random-valued impulse noise," Digit. Signal Process., vol. 20, no. 4, pp. 1010-1018, July 2010.

[20]. http://zh.wikipedia.org/wiki/峰值信噪比

[21]. Xian-Hua Jin; De-Heng Hou, "An Improved Algorithm of Noise Elimination to Image Threshold," Industrial Control and Electronics Engineering(ICICEE), 2012 International Conference on, vol, no., pp.1581,1586, 23-25 Aug. 2012

[22]. Dinesh, R; Navya, V., "New approaches to edge preserved image denoising, " Recent Advances in Computing and Software Systems(RACSS), 2012 International Conference on, vol., no., pp.141,147, 25-27 April 2012

[23]. Vasanth, K.; Jawahar Senthil Kumar, V.; Rajesh, V.; Anitha, "Cascaded decision based Non Linear filters for high density outlier noise removal in images and videos, " Corcuits, Power and Computing Technologies(ICCPCT), 2013 International Conference on ,vol., no., pp.855,860, 20-21 March 2013

[24]. Sahaya Dharshini, AL.; Vasanth, K.; Jawahar SenthilKumar, V.; Selvan, S., "Removal of high density salt and pepper noise using neighborhook based switching filter, " Signal Processing Image Processing & Pattern Recongnition(ICSIPE), 2013 International Conference on, vol., no., pp.224,228, 7-8 Feb. 2013

[25]. Sohail Masood, Ayyaz Hussain, M. Arfan Jaffar, Tae-Sun Choi, "Color differences based fuzzy filter for extremely corrupted color images", Applied Soft Computing, Volume 21, pages 107-118, August 2014.