基于椒盐噪声滤波算法的优化处理
|
摘要
提出了一种针对椒盐噪声滤波算法的优化方法。首先对椒盐噪声图像进行平滑预处理,将结果与椒盐噪声图像做差运算,当差值大于阈值则判定为噪声点;再利用椒盐噪声图像减去噪声像素点得到一幅未被污染的细节图像,利用滤波处理后的图像减去未被污染的细节图像得到噪声滤波处理后的像素点,然后将这些处理后的像素点与未被污染的细节图像镶嵌融合,实现在滤波过程中只对噪声像素点进行滤波处理。实验结果表明,相较于原椒盐滤波算法,优化算法对峰值信噪比提升了2dB左右;同时,优化算法对去核辐照噪声的滤波算法同样具有优化作用,优化处理所需时间小于0. 01 s,图像的保真率得到了提高。
The salt and pepper noise filtering algorithm will cause secondary pollution to the image in the process of filtering. An optimization method for the salt and pepper noise filtering algorithm is propose. Firstly,the image smoothing preprocessing of the salt and pepper noise image is compared with the salt and pepper noise image,and then it is different from the salt and pepper noise image. When the difference is greater than the threshold value,the noise point is determined,and then the noise pixel is subtracted from the salt and pepper noise image to obtain an uncontaminated detail image. The filtered image is subtracted from the uncontaminated detail image to obtain the pixel points after the noise filtering,and then the processed pixels are embedded and fused with the uncontaminated detail image. The aim is to filter noise pixels only in the process of filtering. Real The results show that the 2 dB of the proposed method is higher than that of the original filtering algorithm. At the same time,the filtering algorithm for de-core irradiating noise is also optimized. The processing time is less than 0. 01 s,and the fidelity rate of the image is improved.
The salt and pepper noise filtering algorithm will cause secondary pollution to the image in the process of filtering. An optimization method for the salt and pepper noise filtering algorithm is propose. Firstly,the image smoothing preprocessing of the salt and pepper noise image is compared with the salt and pepper noise image,and then it is different from the salt and pepper noise image. When the difference is greater than the threshold value,the noise point is determined,and then the noise pixel is subtracted from the salt and pepper noise image to obtain an uncontaminated detail image. The filtered image is subtracted from the uncontaminated detail image to obtain the pixel points after the noise filtering,and then the processed pixels are embedded and fused with the uncontaminated detail image. The aim is to filter noise pixels only in the process of filtering. Real The results show that the 2 dB of the proposed method is higher than that of the original filtering algorithm. At the same time,the filtering algorithm for de-core irradiating noise is also optimized. The processing time is less than 0. 01 s,and the fidelity rate of the image is improved.
引文
[1]PITAS I,VENETSANOPOULOS A N.Order statistics in digital image processing[J].Proceedings of the IEEE,1992,80(12):1893-1921.
[2]PAN M S,TANG J T,YANG X L.An adaptive median filter algorithm based on B-spline function[J].International Journal of Automation and Computing,2011,8(1):92-99.
[3]吴海龙,柏正尧,张瑜,等.基于改进PCNN模型的对称中值滤波方法[J].云南大学学报:自然科学版,2018,40(1):43-49.
[4]YUKSEL M E,BESDOK E.A simple neuro-fuzzy impulse detector for efficient blur reduction of impulse noise removal operators for digital images[J].IEEE Transactions on Fuzzy Systems,2005,12(6):854-865.
[5]BOVIK A.Handbook of image and viode processing[M].New York:Academic Press,2000.
[6]RAMDAN Z M.Efficient restoration method for images corrupted with impulse noise[J].Circuits,Systems,and Signal Processing,2012,31(4):1397-1406..
[7]FAN A,WANG G.A mixed denoising method based on median filter and lifting wavelet technology for sewage sensing signal treatment[J].Applied Mechanics and Materials,2013,330(8):967-972.
[8]IBRAHIM H,TOH K K V,MAHYUDDIN M N.Salt and pepper noise detection and reduction using fuzzy switching median filter[J].IEEE Transactions on Consumer Electronics,2008,54(4):1965-1961.
[9]隋修武,胡秀兵,程国栋,等.基于模糊推理的图像椒盐噪声自适应滤波算法[J].微电子学与计算机,2018,35(6):69-74.
[10]DENG H,ZHANG D,WANG T,et al.Objective image-quality assessment for high-resolution photospheric images by median filter-gradient similarity[J].Solar Physics,2015,290(5):1479-1489.
[11]DENG X,MA Y,DONG M.A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN[J].Pattern Recognition Letters,2016,79:8-17.
[12]LI Z Y,LIN G H,XU Y.Modified directional weighted filter for removal of salt&pepper noise[J].Pattern Recognition Letters,2014,40:113-120.
[13]刑藏菊,王守觉,邓浩江.一种基于极值中值的新型滤波算法[J].中国图象图形学报,2001,6(6):533-536.
[14]马继明,宋顾周,王群书,等.辐射图像脉冲去噪方法[J].光子学报,2010,39(11):2107-2111.
[15]杨斌,赵立宏,邓骞.基于图像修复技术的抗核辐射图像恢复方法[J].南华大学学报:自然科学版,2016,30(4):56-61.
[16]CHEN P Y,LIEN C Y.An efficient edge-preserving algorithm for removal of salt-and-pepper noise[J].IEEE Signal Processing Letters,2008,15:833-836.
[17]YIN L,YANG R,GABBOUJ M,et al.Weighted median filters:a tutorial[J].IEEE Transactions on Circuits and SystemsⅡ:Analog and Digital Signal Processing,1996,43(3):157-192.
[18]张旭明,徐滨士,董世运.用于图像处理的自适应中值滤波[J].计算机辅助设计与图形学学报,2005,17(2):295-299.
[2]PAN M S,TANG J T,YANG X L.An adaptive median filter algorithm based on B-spline function[J].International Journal of Automation and Computing,2011,8(1):92-99.
[3]吴海龙,柏正尧,张瑜,等.基于改进PCNN模型的对称中值滤波方法[J].云南大学学报:自然科学版,2018,40(1):43-49.
[4]YUKSEL M E,BESDOK E.A simple neuro-fuzzy impulse detector for efficient blur reduction of impulse noise removal operators for digital images[J].IEEE Transactions on Fuzzy Systems,2005,12(6):854-865.
[5]BOVIK A.Handbook of image and viode processing[M].New York:Academic Press,2000.
[6]RAMDAN Z M.Efficient restoration method for images corrupted with impulse noise[J].Circuits,Systems,and Signal Processing,2012,31(4):1397-1406..
[7]FAN A,WANG G.A mixed denoising method based on median filter and lifting wavelet technology for sewage sensing signal treatment[J].Applied Mechanics and Materials,2013,330(8):967-972.
[8]IBRAHIM H,TOH K K V,MAHYUDDIN M N.Salt and pepper noise detection and reduction using fuzzy switching median filter[J].IEEE Transactions on Consumer Electronics,2008,54(4):1965-1961.
[9]隋修武,胡秀兵,程国栋,等.基于模糊推理的图像椒盐噪声自适应滤波算法[J].微电子学与计算机,2018,35(6):69-74.
[10]DENG H,ZHANG D,WANG T,et al.Objective image-quality assessment for high-resolution photospheric images by median filter-gradient similarity[J].Solar Physics,2015,290(5):1479-1489.
[11]DENG X,MA Y,DONG M.A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN[J].Pattern Recognition Letters,2016,79:8-17.
[12]LI Z Y,LIN G H,XU Y.Modified directional weighted filter for removal of salt&pepper noise[J].Pattern Recognition Letters,2014,40:113-120.
[13]刑藏菊,王守觉,邓浩江.一种基于极值中值的新型滤波算法[J].中国图象图形学报,2001,6(6):533-536.
[14]马继明,宋顾周,王群书,等.辐射图像脉冲去噪方法[J].光子学报,2010,39(11):2107-2111.
[15]杨斌,赵立宏,邓骞.基于图像修复技术的抗核辐射图像恢复方法[J].南华大学学报:自然科学版,2016,30(4):56-61.
[16]CHEN P Y,LIEN C Y.An efficient edge-preserving algorithm for removal of salt-and-pepper noise[J].IEEE Signal Processing Letters,2008,15:833-836.
[17]YIN L,YANG R,GABBOUJ M,et al.Weighted median filters:a tutorial[J].IEEE Transactions on Circuits and SystemsⅡ:Analog and Digital Signal Processing,1996,43(3):157-192.
[18]张旭明,徐滨士,董世运.用于图像处理的自适应中值滤波[J].计算机辅助设计与图形学学报,2005,17(2):295-299.