消除椒盐噪声的基于纹理特征的决策滤波
|
摘要
图像中椒盐噪声的有效去除,取决于噪声检测和噪声灰度估测的准确性,但现有的滤波算法在噪声检测和噪声灰度估测上的准确性不高。因此,提出了基于图像纹理特征的决策滤波算法。算法根据椒盐噪声的灰度最值特征和独立性,以及图像纹理的特征进行噪声检测,将噪声与信号像素准确地区分开。算法根据纹理中像素灰度的平滑变化特征,将邻域中的信号像素进行分组,然后基于相关性与正态概率分布的意义,取与邻域均值最接近的分组的中值作为噪声像素的估测值。实验的结果证明,所提出的算法检测噪声更加准确,其去噪结果对应的峰值信噪比(PSNR)比现有的算法平均提高1.9 dB以上,图像增强因子(IEF)比现有的算法平均提高119以上。因此,相对于现有的算法,所提出的算法在去噪性能上具有显著的优越性。
The effectiveness of salt and pepper noise removal lies on the noise detection and the intensity estimation of noisy pixel, but existing filters show low performance for them. In view of this problem, a decision filter based on image texture features is proposed. The proposed method performs noise detection by taking full advantage of the characteristics of salt and pepper noise, i.e., the noise takes extreme intensity values and is independent on noise free pixels, as well as the texture features of image, thus, correctly discriminates the noisy pixels from the noise free pixels. Based on the varied intensity of image texture, the proposed method groups the neighbor noise free pixels, in the light of correlation and significance of normal probability distribution, it takes the median of the group, which is closest to the mean of neighbor noise free pixels; as the intensity of noisy pixel. The experimental results show that, the proposed method can perform a more accurate noise detection compared with the existing filters, it resulted that PSNR increases averagely by more than 1.9 dB, IEF increases averagely by more than 119. Thus, it can conclude that the denoising performance of the proposed method is superior to the existing filters.
The effectiveness of salt and pepper noise removal lies on the noise detection and the intensity estimation of noisy pixel, but existing filters show low performance for them. In view of this problem, a decision filter based on image texture features is proposed. The proposed method performs noise detection by taking full advantage of the characteristics of salt and pepper noise, i.e., the noise takes extreme intensity values and is independent on noise free pixels, as well as the texture features of image, thus, correctly discriminates the noisy pixels from the noise free pixels. Based on the varied intensity of image texture, the proposed method groups the neighbor noise free pixels, in the light of correlation and significance of normal probability distribution, it takes the median of the group, which is closest to the mean of neighbor noise free pixels; as the intensity of noisy pixel. The experimental results show that, the proposed method can perform a more accurate noise detection compared with the existing filters, it resulted that PSNR increases averagely by more than 1.9 dB, IEF increases averagely by more than 119. Thus, it can conclude that the denoising performance of the proposed method is superior to the existing filters.
引文
[1] ZHANG J,WU J,COATRIEUX J L,et al.A correlation based strategy for the acceleration of nonlocal means filtering algorithm [J].Mathematical Problems in Engineering,2016,DOI:10.1155/2016/5483485.
[2] WANG X,SHEN S,SHI G,et al.Iterative non-local means filter for salt and pepper noise removal [J].Journal of Visual Communication and Image Representation,2016(38):440-450.
[3] 谢英红,李凌,何宇清.基于双边滤波的协方差目标跟踪算法[J].电子测量与仪器学报,2016,30(8):1282-1287.XIE Y H,LI L,HE Y Q.Covariance object tracking algorithm based on bilateral filtering [J].Journal of Electronic Measurement and Instrumentation,2016,30(8):1282-1287.
[4] BALASUBRAMANIAN G,CHILAMBUCHELVAN A,VIJAYAN S,et al.An extremely fast adaptive high-performance filter to remove salt and pepper noise using overlapping medians in images [J].Imaging Science Journal,2016,64(5):241-252.
[5] ZHENG D,DA F,KEMAO Q,et al.Phase-shifting profilometry combined with Gray-code patterns projection:Unwrapping error removal by an adaptive median filter[J].Optics Express,2017,25(5):4700-4713.
[6] 李倩,朱磊,邵文权.SAR图像各向异性扩散滤波算法 [J].国外电子测量技术,2016,35(2):59-64.LI Q,ZHU L,SHAO W Q.Anisotropic diffusion filtering algorithm for SAR images[J].Foreign Electronic Measurement Technology,2016,35(2):59-64.
[7] PARK H H.Making joint-histogram-based weighted median filter much faster [J].Transactions on Information and Systems,2015,E98-D(3):721-725.
[8] BANDALA-HERNANDEZ H C,ROCHA-PéREZ J M,DíAZ-SáNCHEZ A,et al.Weighted median filters:An analog implementation [J].Integration,the VLSI Journal,2016(55):227-231.
[9] JIN L H,XIONG C Q,LI D H.Adaptive center-weighted median filter [J].Journal of Huazhong University of Science and Technology,2008,36(8):9-12.
[10] SADI F,LEE S Y,HASAN M K.Removal of ring artifacts in computed tomographic imaging using iterative center weighted median filter [J].Computers in Biology and Medicine,2010,40(1):109-118.
[11] WANG G,LI D,PAN W,et al.Modified switching median filter for impulse noise removal [J].Signal Processing,2010,90(12):3213-3218.
[12] 张皓,陈明亮.邻近移动窗消除高密度椒盐噪声的中值滤波[J].电子测量与仪器学报,2018,32(9):169-175.ZHANG H,CHEN M L.Median filtering for eliminating high density salt and pepper noise by adjacent moving window[J].Journal of Electronic Measurement and Instrumentation,2018,32(9):169-175.
[13] LU C T,CHOU T C.Denoising of salt-and-pepper noise corrupted image using modified directional-weighted-median filter [J].Pattern Recognition Letters,2012,33(10):1287-1295.
[14] 陈健,郑绍华,余轮,等.基于方向的多阈值自适应中值滤波改进算法[J].电子测量与仪器学报,2013,27(2):156-161.CHEN J,ZHENG SH H,YU L,et al.Improved algorithm for adaptive median filter with multi-threshold based on directional information[J].Journal of Electronic Measurement and Instrument,2013,27(2):156-161.
[15] 张倩.基于改进伪中值滤波和非局部均值滤波的红外图像滤波方法[J].工矿自动化,2014,40(12):57-60.ZHANG Q.A filtering method for infrared image based on improved pseudo median filtering and non-local means filtering[J].Industry and Mine Automation,2014,40(12):57-60.
[16] 周开军,周鲜成,申立智,等.基于多变量属性分类的图像形态滤波方法研究[J].仪器仪表学报,2015,36(8):1735-1743.ZHOU K J,ZHOU X CH,SHEN L ZH,et al.Image morphological filtering method based on multivariate attributes classification [J].Chinese Journal of Scientific Instrument,2015,36(8):1735-1743.
[17] ZHANG C B,WANG K F.A switching median-mean filter for removal high-density impulse noise from digital images [J].Optik,2015,126(9-10):956-961.
[18] MEHER S K,SINGHAWAT B.An improved recursive and adaptive median filter for high density impulse noise[J].AEU-International Journal of Electronics and Communications,2014,68(12):1173-1179.
[19] GUPTA V,CHAURASIA V,SHANDILYA M.Random-valued impulse noise removal using adaptive dual threshold median filter [J].Journal of Visual Communication and Image Representation,2015,(26):296-304.
[20] 史再峰,许泽昊,庞科,等.一种基于开关型加权中值滤波的随机脉冲噪声去除方法[J].南开大学学报,2018,51(4):63-67.SHI Z F,XU Z H,PANG K,et al.A random-value impulse noise removal method based on switching weighted median filter[J].Acta Scientiarum Naturalium Universitatis Nankaiensis,2018,51(4):63-67.
[21] KHAN S,LEE D H.An adaptive dynamically weighted median filter for impulse noise removal[J].Eurasip Journal on Advances in Signal Processing,2017(1):67.
[22] 牛敏,邬战军,牛燕雄,等.一种基于排序统计理论的快速图像中值滤波法[J].电子测量技术,2015,38(6):60-63.NIU M,WU ZH J,NIU Y X,et al.Fast image median filtering method based on statistical theory [J].Electronic Measurement Technology,2015,38(6):60-63.
[23] KUMAR S A,PRIYADARSHI K,BIBHUPRASAD M.Neighborhood decision based impulse noise filter[J].IET Image Processing,2018,12(7):1222-1227.
[24] BALASUBRAMANIAN G,CHILAMBUCHELVAN A,VIJAYAN S,et al.Probabilistic decision based filter to remove impulse noise using patch else trimmed median[J].AEU-International Journal of Electronics and Communications,2016,70(4):471-481.
[2] WANG X,SHEN S,SHI G,et al.Iterative non-local means filter for salt and pepper noise removal [J].Journal of Visual Communication and Image Representation,2016(38):440-450.
[3] 谢英红,李凌,何宇清.基于双边滤波的协方差目标跟踪算法[J].电子测量与仪器学报,2016,30(8):1282-1287.XIE Y H,LI L,HE Y Q.Covariance object tracking algorithm based on bilateral filtering [J].Journal of Electronic Measurement and Instrumentation,2016,30(8):1282-1287.
[4] BALASUBRAMANIAN G,CHILAMBUCHELVAN A,VIJAYAN S,et al.An extremely fast adaptive high-performance filter to remove salt and pepper noise using overlapping medians in images [J].Imaging Science Journal,2016,64(5):241-252.
[5] ZHENG D,DA F,KEMAO Q,et al.Phase-shifting profilometry combined with Gray-code patterns projection:Unwrapping error removal by an adaptive median filter[J].Optics Express,2017,25(5):4700-4713.
[6] 李倩,朱磊,邵文权.SAR图像各向异性扩散滤波算法 [J].国外电子测量技术,2016,35(2):59-64.LI Q,ZHU L,SHAO W Q.Anisotropic diffusion filtering algorithm for SAR images[J].Foreign Electronic Measurement Technology,2016,35(2):59-64.
[7] PARK H H.Making joint-histogram-based weighted median filter much faster [J].Transactions on Information and Systems,2015,E98-D(3):721-725.
[8] BANDALA-HERNANDEZ H C,ROCHA-PéREZ J M,DíAZ-SáNCHEZ A,et al.Weighted median filters:An analog implementation [J].Integration,the VLSI Journal,2016(55):227-231.
[9] JIN L H,XIONG C Q,LI D H.Adaptive center-weighted median filter [J].Journal of Huazhong University of Science and Technology,2008,36(8):9-12.
[10] SADI F,LEE S Y,HASAN M K.Removal of ring artifacts in computed tomographic imaging using iterative center weighted median filter [J].Computers in Biology and Medicine,2010,40(1):109-118.
[11] WANG G,LI D,PAN W,et al.Modified switching median filter for impulse noise removal [J].Signal Processing,2010,90(12):3213-3218.
[12] 张皓,陈明亮.邻近移动窗消除高密度椒盐噪声的中值滤波[J].电子测量与仪器学报,2018,32(9):169-175.ZHANG H,CHEN M L.Median filtering for eliminating high density salt and pepper noise by adjacent moving window[J].Journal of Electronic Measurement and Instrumentation,2018,32(9):169-175.
[13] LU C T,CHOU T C.Denoising of salt-and-pepper noise corrupted image using modified directional-weighted-median filter [J].Pattern Recognition Letters,2012,33(10):1287-1295.
[14] 陈健,郑绍华,余轮,等.基于方向的多阈值自适应中值滤波改进算法[J].电子测量与仪器学报,2013,27(2):156-161.CHEN J,ZHENG SH H,YU L,et al.Improved algorithm for adaptive median filter with multi-threshold based on directional information[J].Journal of Electronic Measurement and Instrument,2013,27(2):156-161.
[15] 张倩.基于改进伪中值滤波和非局部均值滤波的红外图像滤波方法[J].工矿自动化,2014,40(12):57-60.ZHANG Q.A filtering method for infrared image based on improved pseudo median filtering and non-local means filtering[J].Industry and Mine Automation,2014,40(12):57-60.
[16] 周开军,周鲜成,申立智,等.基于多变量属性分类的图像形态滤波方法研究[J].仪器仪表学报,2015,36(8):1735-1743.ZHOU K J,ZHOU X CH,SHEN L ZH,et al.Image morphological filtering method based on multivariate attributes classification [J].Chinese Journal of Scientific Instrument,2015,36(8):1735-1743.
[17] ZHANG C B,WANG K F.A switching median-mean filter for removal high-density impulse noise from digital images [J].Optik,2015,126(9-10):956-961.
[18] MEHER S K,SINGHAWAT B.An improved recursive and adaptive median filter for high density impulse noise[J].AEU-International Journal of Electronics and Communications,2014,68(12):1173-1179.
[19] GUPTA V,CHAURASIA V,SHANDILYA M.Random-valued impulse noise removal using adaptive dual threshold median filter [J].Journal of Visual Communication and Image Representation,2015,(26):296-304.
[20] 史再峰,许泽昊,庞科,等.一种基于开关型加权中值滤波的随机脉冲噪声去除方法[J].南开大学学报,2018,51(4):63-67.SHI Z F,XU Z H,PANG K,et al.A random-value impulse noise removal method based on switching weighted median filter[J].Acta Scientiarum Naturalium Universitatis Nankaiensis,2018,51(4):63-67.
[21] KHAN S,LEE D H.An adaptive dynamically weighted median filter for impulse noise removal[J].Eurasip Journal on Advances in Signal Processing,2017(1):67.
[22] 牛敏,邬战军,牛燕雄,等.一种基于排序统计理论的快速图像中值滤波法[J].电子测量技术,2015,38(6):60-63.NIU M,WU ZH J,NIU Y X,et al.Fast image median filtering method based on statistical theory [J].Electronic Measurement Technology,2015,38(6):60-63.
[23] KUMAR S A,PRIYADARSHI K,BIBHUPRASAD M.Neighborhood decision based impulse noise filter[J].IET Image Processing,2018,12(7):1222-1227.
[24] BALASUBRAMANIAN G,CHILAMBUCHELVAN A,VIJAYAN S,et al.Probabilistic decision based filter to remove impulse noise using patch else trimmed median[J].AEU-International Journal of Electronics and Communications,2016,70(4):471-481.