自然影像常受到脈衝雜訊的污染，而脈衝雜訊類似影像中的高頻訊號，本論文首先分析影像中像素間的相似性，並將所有像素分類到不同頻帶，依據每個頻帶的性質使用不同大小的遮罩來衰減脈衝雜訊。本論文提出三個脈衝雜訊濾除方法：（一）適應性邊緣保存脈衝雜訊濾波方法、（二）兩階段脈衝雜訊濾波方法、（三）以DCT(離散餘弦轉換)為基礎的適應性分頻多形態脈衝雜訊濾除方法。第一種方法依雜訊比例的多寡得到適應性遮罩及臨界值，再以「邊緣」特徵來偵測並濾除脈衝雜訊；第二種方法先以遮罩中出現機率最高的「邊緣」特徵來保留影像細節，接著再偵測像素是否為脈衝雜訊並將之濾除；第三種方法使用PSNR定義影像裡每一個8＊8區塊的高頻與低頻資訊，再根據每區塊的高低頻資訊以不同的遮罩來衰減脈衝雜訊。實驗結果顯示本論文所提之適應性邊緣保存脈衝雜訊濾除方法比已知的方法提升濾波後影像的PSNR值5%至30%。兩階段脈衝雜訊濾除方法減少像素被誤判為雜訊的機率，提升濾波後影像的PSNR值0.5dB至2dB。適應性分頻多形態脈衝雜訊濾波方法提升濾波後影像的PSNR值7%至15%。
電腦無法判斷影像是否已受到脈衝雜訊污染及污染的程度，因此造成許多已知的疊代脈衝雜訊濾波方法無法有效的去除雜訊而模糊原始影像的細節。本論文根據影像濾波前與濾波後的差異，提出基於前後兩次濾波影像PSNR值變化及被濾波像素之總數的自動收斂疊代脈衝雜訊濾波方法，並從疊代濾波的過程中推導出適應性臨界值，讓疊代雜訊濾波方法可以自動地在有限次數下停止濾除雜訊。實驗證明與他人非自動疊代雜訊濾波方法比較，本論文所提方法所得PSNR值的平均誤差低於0.3dB。
此外，本論文將像素相似性的概念應用於衰減視訊雜訊及視訊畫面的穩定，實驗結果顯示本論文所提方法在衰減視訊雜訊上可以提升影像壓縮比90%，在視訊畫面穩定上可將晃動振幅降至2個像素。

Natural images are usually corrupted with impulse noises which is similar to high-frequency signals in an image. Therefore, this thesis analyzes the similarity between a pixel and its neighbors to determine the pixel belonging to which frequency band. According to the characteristic of each frequency band, this thesis proposes an adaptive edge-preserved median filtering method. “Edge” is an important feature of pixel similarity. A second impulse noise filtering method which preserves image details via the eight highest probability of the "edge" feature is proposed. A third impulse noise reduction method by using the subband concept and DCT (Discrete Cosine Transform) is also proposed. In this method an image is divided into low-frequency blocks and high-frequency blocks by using PSNR (peak signal-to-noise-ratio) checking and an appropriate working window for each type of blocks is employed to suppress impulse noises. Experimental results show that the improvement rate of the PSNR value of the first proposed method to other published methods is ranging from 5% to 30%. The second proposed noise filtering method can reduce the probability of pixels being misclassified as noise. The improved PSNR value is ranging from 0.5 dB to 2 dB. The improvement rate of the PSNR value of the third noise filtering method is ranging from 7% to 15%.
Whether images are corrupted by impulse noises and the degree of corruption are unknown a priori, and thus published iterative impulse noise filtering methods cannot adaptively reduce noise, resulting in a smoothing image or unclear de-noising. For this reason, in the second part this thesis proposes an automatic convergence iterative impulse noise filtering method using PSNR checking and filtered pixels detection to estimate the difference between two consecutive filtered images. An adaptive threshold is defined to make the iterative impulse noise filtering methods stop automatically in finite steps. Experiments showed that an almost optimal filtered image in which the average difference of the PSNR value between our method and other nonautomatic methods below 0.3 dB is obtained.
In the third part this thesis applies the concept of pixel similarity to video noise reduction and video stabilization. Experimental results show that video noise reduction can effectively improve the image compression rate to 90%, and video stabilization can reduce the vibration amplitude to 2 pixels.

[1] F. Ahmed and S. Das, “Removal of high-density salt-and-pepper noise in images with an iterative fuzzy filter using alpha-trimmed mean,” IEEE Transactions on Fuzzy Systems, vol. 22, pp. 1352-1358, Oct. 2014.
[2] S. Akkoul, R. Lédée, R. Leconge and R. Harba, “A new adaptive switching median filter,” IEEE Signal Processing Letters, vol. 17, pp. 587-590, Apr. 2010.
[3] G. R. Arce and M. P. McLoughlin, “Theoretical analysis of the MAX/median filter,” IEEE Transactions on Acoustics., Speech and Signal Processing, vol. ASSP-35, pp. 60-69, Jan. 1987.
[4] L. Bai, Q. Chen, G. Gu and B. Zhang, “Time-space noise processing technique for low light level (LLL) image,” International Conference on Signal Processing, vol. 2, pp. 1052-1055, Oct. 1998.
[5] D. Barash, “A fundamental relationship between bilateral filtering, adaptive smoothing, and the nonlinear diffusion equation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 844-847, Jun. 2002.
[6] J. Boyce, “Noise reduction of image sequences using adaptive motion compensated frame averaging,” IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 461–464, Mar. 1992.
[7] J. C. Brailean, R. P. Kleihorst, S. Efstratiadis, A. K. Katsaggelos and R. L. Lagendijk “Noise reduction filters for dynamic image sequences: a review,” Proceedings of the IEEE, vol. 83, pp. 1272-1292, Sept. 1995.
[8] G. Cao, Y. Zhao and R. Ni, “Edge-based blur metric for tamper detection”, Journal of Information Hiding and Multimedia Signal Processing, vo1. 1, pp. 20-27, Jan. 2010.
[9] H. C. Chang, S. H. Lai and K. R. Lu, “A robust real-time video stabilization algorithm,” Journal of Visual Communication and Image Representation, vol. 17, pp. 659-673, June 2006.
[10] C. C. Chang, C. C. Lin and Y. S. Hu, “An SVD oriented watermark embedding scheme with high qualities for the restored images,” International Journal of Innovative Computing, Information and Control, vol. 3, pp. 609-620, 2007.
[11] Q. Chen, L. Bai and B. Zhang, “Real-time adaptive noise processing in low light level images,” International Conference on Signal Processing, pp. 606-609, 1996.
[12] C. H. (T. H.) Chen, C. Y. Chen and C. H. Chen, “Intelligent adaptive subband-based multi-state median filter in lowly-corrupted Images,” International Journal of Innovative Computing, Information and Control (IJICIC), vol. 5, pp. 2917-2926, Sep. 2009.
[13] T. H. (C. H.) Chen, C. Y. Chen and C. H. Chen, “An adaptive random-valued impulse noise reduction method based on noise ratio estimation in highly corrupted images,” IEEE 2007 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP07), pp. 523-526, Taiwan, Nov. 26-28, 2007.
[14] T. H. (C. H.) Chen, C. Y. Chen and T. Y. Chen, “An impulse noise reduction method by adaptive pixel-correlation,” 2006 IEEE International Conference on Innovative Computing, Information and Control (ICICIC-06), pp. 257-260, Beijing, P. R. China, Aug. 2006.
[15] T. Y. Chen, T. H. (C. H.) Chen, S. F. Huang, and Y. F. Li, “An adjustable multipath flatted-hexagon search algorithm for block motion estimation,” IEEE 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP), pp. 431-434, Pasadena, California, USA, Dec. 18-20, 2006.
[16] T. Y. Chen, T. H. (C. H.) Chen and D. J. Wang, “A cost-effective people-counter for passing through a gate based on image processing,” International Journal of Innovative Computing, Information and Control (IJICIC), vol. 5, pp. 785-800, Mar. 2009.
[17] T. Y. Chen, T. H. (C. H.) Chen, D. J. Wang, and Y. C. Chiou, “Real-time video object segmentation algorithm based on change detection and background updating,” International Journal of Innovative Computing, Information and Control (IJICIC), vol. 5, pp. 1797-1810, July 2009.
[18] C. H. Chen, C. W. Hsu, and C. H. Chen, “Video stabilization by feature-block motion estimation,” IEEE 8th International Conference on Intelligent Systems Design and Applications (ISDA08), Kaohsiung, Taiwan, pp. 557-560, Nov. 26-28, 2008.
[19] T. Chen, K. K. Ma and L. H. Chen, “Tri-state median filter for image denoising,” IEEE Transactions on Image Processing, vol. 8, pp. 1834-1838, Dec. 1999.
[20] T. H. (C. H.) Chen, C. P. Tsai, and T. Y. Chen, “An intelligent impulse noise detection method by adaptive subband-based multi-state median filtering,” 2007 IEEE International Conference on Innovative Computing, Information and Control (ICICIC-07), Kumamoto, Japan, Sept. 5-7, 2007.
[21] T. Chen and H. R. Wu, “Space variant median filters for the restoration of impulse noise corrupted images,” IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, vol. 48, pp. 784-789, Aug. 2001.
[22] V. Crnojevi, “Impulse noise filter with adaptive MAD-based threshold,” 2005 IEEE International Conference on Image Processing (ICIP), pp. 37-40, Sept. 2005.
[23] Y. Dong and S. Xu, “A new directional weighted median filter for removal of random-value impulse noise,” IEEE Signal Processing Letters, vol. 14, pp. 193-196, Mar. 2007.
[24] Z. Duric and A. Rosenfeld, “Stabilization of image sequences,” Univ. Maryland, Tech.. Rep. CAR-TR-778, July 1995.
[25] M. Elad, “On the origin of the bilateral filter and ways to improve it,” IEEE Transactions on Image Processing, vol. 11, pp. 1141-1151, Oct. 2002.
[26] H. L. Eng and K. K. Ma, “Noise adaptive soft-switching median filter,” IEEE Transactions on Image Processing, vol. 10, pp. 242-251, Feb. 2001.
[27] S. Esakkirajan, T. Veerakumar, A. Subramanyam and C. PremChand, “Removal of high density salt and pepper noise through modified decision based unsymmetric trimmed median filter,” IEEE Signal Processing Letters, vol. 18, pp. 287–290, May 2011.
[28] S. Etrurk, “Digital image stabilization with sub-image phase correlation based global motion estimation”, IEEE Transactions on Consumer Electronics, vol. 49, pp. 1320-1325, Nov. 2003.
[29] M. Gabbouj, E. J. Coyle, J. Neal, and C. Callagher, “An overview of median and stack filtering,” Circuits System Signal Process., vol. 11, pp. 7-45, Jan. 1992.
[30] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Englewood Cliffs, NJ: Prentice-Hall, 2002.
[31] X. H. Han, Y. W. Chen and J. M. Lei, “A spatio-chromatic ICA based noise reduction in color images,” International Journal of Innovative Computing, Information and Control, vol. 4, pp. 661-670, Mar. 2008.
[32] M. Hansen, P. Anandan, K. Dana. G. V. Wal and P. Burt, “Real-time scene stabilization and mosaic costruction,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 54-62, Dec. 1994.
[33] H. Hosseini, F. Hessar and F. Marvasti, “Real-time impulse noise suppression from images using an efficient weighted-average filtering,” IEEE Signal Processing Letters, vol. 22, pp. 1050-1054, Aug. 2015.
[34] T. S. Huang, Ed., Image Sequence Analysis. Berlin: Springer-Verlag, pp. 289-290, 1981.
[35] M. Jin and J. Z. Song, “An adaptive bilateral filtering method for image processing,” Opto-Electronic Engineering, vol. 31, pp. 2, July 2004.
[36] 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. 984-993, Sep. 1991.
[37] H. Y. Lee, W. L. Hoo and C. S. Chan, “Color video denoising using epitome and sparse coding,” Expert Systems with Applications, vol. 42, pp. 751-759, Feb. 2015.
[38] S. W. Lee, V. Maik, J. Jang, J. Shin and J. Paik, “Noise-adaptive spatio-temporal filter for real-time noise removal in low light level images,” IEEE Transactions on Consumer Electronics, vol. 51, pp. 648-653, May 2005.
[39] Y. H. Lee and S. Tantaratana, “Decision-based order statistics filters,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 38, pp. 406-420, Mar. 1990.
[40] T. C. Lin, “Decision-based fuzzy image restoration for noise reduction based on evidence theory,” Expert Systems with Applications, vol. 38, pp. 8303-8310, July 2011.
[41] A. Litvin, J. Konrad and W. C. Karl, “Probabilistic video stabilization using Kalman filtering and mosaicking,” Proc. of IS&T/SPIE Symposium in Electronic Imaging, Image and Video Communciations and Processing, vol. 5022, pp. 663-674, Jan. 2003.
[42] W. Luo, “An efficient detail-preserving approach for removing impulse noise in images,” IEEE Signal Processing Letters, vol. 13, pp. 413-416, July, 2006.
[43] W. Luo, “A new impulse detector based on order statistics,” AEU-International Journal of Electronics and Communication, vol. 60, pp. 462-466, June 2006.
[44] Y. Matsushita, E. Ofek, X. Tang and H. Y. Shum, “Full-frame video stabilization,” IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 50-57, June 2005.
[45] H. B. Mitchell and N. Mashkit, “Noise smoothing by a fast k-nearest neighbour algorithm,” Signal Processing: Image Communication, vol. 4, pp. 227-232, June 1992.
[46] K. Miyata and A. Taguchi, “Spatio-temporal separable data-dependent weighted average filtering for restoration of the image sequences,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-02), vol. 4, pp. 3696–3699, May 2002.
[47] C. Morimoto and R. Chellappa. “Automatic digital image stabilization,” IEEE Conference on Pattern Recognition, Aug. 1996.
[48] P. E. Ng and K. K. Ma, “A switching median filter with boundary discriminative noise detection for extremely corrupted images,” IEEE Transactions on Image Processing, vol. 15, pp. 1506-1516, June 2006.
[49] I. Pitas and A. N. Venetsanopoulos, “Nonlinear digital filters: principles and applications,” Dordrecht: Kluwer Academic Publishers, 1990.
[50] G. Pok, J. C. Liu, and A. S. Nair, “Selective removal of impulse noise based on homogeneity level information,” IEEE Transactions on Image Processing, vol. 12, pp. 85-92, Jan. 2003.
[51] T. Sun and Y. Neuvo, “Details-preserving median based filters in image processing,” Pattern Recognition Letters, vol. 15, pp. 341-347, Apr. 1994.
[52] C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color image,” IEEE Six International Conference on Computer Vision, pp. 839-846, Jan. 1998.
[53] H. J. Wang and Y. Deng, “Spatial clustering method based on cloud model,” IEEE International Conference on Fuzzy System and Knowledge Discovery, vol. 2, pp. 272–276, Aug. 2007.
[54] H. Wang, J. Liang and C.-C. J. Kuo, “Overview of robust video streaming with network coding,” Journal of Information Hiding and Multimedia Signal Processing, vo1. 1, pp. 36-50, Jan. 2010.
[55] Z. Wang and D. Zhang, “Progressive switching median filter for the removal of impulse noise from highly corrupted images,” IEEE Transactions on Circuits and Systems, vol. 46, pp. 78-80, Jan. 1999.
[56] M. Weng and M. He, “Image detection based on susan method and integrated feature matching,” International Journal of Innovative Computing, Information and Control, vol. 4, pp. 671-680, 2008.
[57] Y. Wexler, E. Shechtman and M. Irani, “Space-time video completion,” IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 120-127, July 2004.
[58] B. Xiong and Z. Yin, “A universal denoising framework with a new impulse detector and nonlocal means,” IEEE Transactions on Image Processing, vol. 21, pp. 1663-1675, Apr. 2012.
[59] X. Xu, E. L. Miller, D. Chen, and M. Sarhadi, “Adaptive two-pass rank order filter to remove impulse noise in highly corrupted images,” IEEE Transactions on Image Processing, vol. 13, pp. 238-247, Feb. 2004.
[60] N. Yamashita, M. Ogura, J. Lu, H. Sekiya, and T. Yahagi, “A random-valued impulse noise detector using level detection,” 2005 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 6292–6295, May 2005.
[61] Y. S. Yao and R. Chellappa, “Electronic stabilization and feature tracking in long image sequences,” Univ. Maryland, Tech.. Rep. CAR-TR-790, Sept. 1995.
[62] O. Yli-Harja, J. Astola and Y. Neuvo, “Analysis of the properties of median and weighted median filters using threshold logic and stack filter representation,” IEEE Transactions on Signal Processing, vol. 39, pp. 395-410, Feb. 1991.
[63] S. Zhang and M. A. Karim, “A new impulse detector for switching median filters,” IEEE Signal Processing Letters, vol. 9, pp. 360-363, Nov. 2002.
[64] Z. Zhang and Y. Zhao, “Multiple description image coding based on fractal,” International Journal of Innovative Computing, Information and Control, vol. 3, pp. 1615-1623, 2007.
[65] Z. Zhou, “Cognition and removal of impulse noise with uncertainty,” IEEE Transactions on Image Processing, vol. 21, pp. 3157–3167, Jul. 2012.
[66] V. Zlokolica, W. Philips, and D. Van De Ville, “Robust non-linear filtering for video processing,” 14th International Conference on Digital Signal Processing, vol. 2, pp. 571-574, July 2002.