HSI空间上高噪声彩色图像去噪方法研究

doi:10.3778/j.issn.1673-9418.1912010

摘要/Abstract

摘要：

针对彩色图像中噪声难以去除的问题，根据HSI空间独特的色彩分离特点，对受高噪声污染的彩色图像的噪声去除进行了研究。首先将彩色图像投影到色彩特征空间HSI中，将色彩信息与亮度特征信息进行分离操作，然后对该空间中的色彩分量H和S提出极坐标下距离阈值去噪方法进行处理，在保持色彩不失真的情况下去除噪声。同时对亮度特征分量I进行多尺度变换得到高低频子图，根据高频子图中噪声突变频繁的特点提出自适应梯度阈值去噪方法去除高频中噪声以提高图像质量；采用稀疏去噪方法对低频子图中少量噪声进行处理；最后进行相应逆变换得到最终的彩色图像。实验结果表明，所提出的去噪方法在视觉上和PSNR、RMSE、SSIM、RE这些客观指标上均达到了良好的噪声去除效果。

关键词: 彩色图像, HSI空间, 非下采样剪切波变换（NSST）, 去噪方法

Abstract:

In view of the difficulty of noise removal in color images, according to the unique color separation charac-teristics of HSI space, the noise removal of color image polluted by high noise is studied. Firstly, the color image is projected into the HSI of the color feature space, and the color information is separated from the intensity feature information. Then, the color components H and S in the space are processed with a method of distance threshold denoising in polar coordinates, so as to remove the noise without losing the true color. At the same time, multi-scale transformation is carried out on intensity feature component I to obtain the high and low frequency subgraph. According to the frequent noise mutation in the high frequency subgraph, an adaptive gradient threshold denoising method is proposed to remove the noise in the high frequency to improve the image quality. The sparse denoising method is adopted to deal with a small amount of noise in the low-frequency subgraph. Finally, the corresponding inverse transformation is carried out to obtain the final color image. The experimental results show that the method in this paper achieves good denoising effect in vision and objective indexes such as PSNR, RMSE, SSIM and RE.

Key words: color image, HSI space, non-subsample shearlet transform (NSST), denoising method

杨培，高雷阜，訾玲玲. HSI空间上高噪声彩色图像去噪方法研究[J]. 计算机科学与探索, 2020, 14(11): 1943-1955.

YANG Pei, GAO Leifu, ZI Lingling. Research on High Noise Color Image Denoising Method in HSI Space[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(11): 1943-1955.

参考文献

[1] He L, Li C M, Xu C Y. Intensity statistics-based HSI diffu-sion for color photo denoising[C]//Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, Jun 24-26, 2008. Washington: IEEE Computer Society, 2008: 1-8.
[2] Andreas K, Mongi A. Digital color image processing[M]. New York: John Wiley & Sons, 2008.
[3] Zhang Y Q, Zhang P L, Wang G D, et al. Denoising method for color images based on chrominance model and curvelet transform[J]. Journal of Image and Graphics, 2012, 17(12): 1472-1477.张云强, 张培林, 王国德, 等. 基于曲波变换和色度模型的彩色图像去噪[J]. 中国图象图形学报, 2012, 17(12): 1472-1477.
[4] Ono S, Yamada I. Decorrelated vectorial total variation[C]// Proceedings of the 2014 IEEE Conference on Computer Vi-sion and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 4090-4097.
[5] Jia D, Meng X F, Zhang Y F, et al. Edge preserving denois-ing of color image through controlling the gradient vector[J]. Journal of Image and Graphics, 2014, 19(4): 493-501.贾迪, 孟祥福, 张一飞, 等. 梯度矢量扩散控制实现边缘保持的彩色图像去噪[J]. 中国图象图形学报, 2014, 19(4): 493-501.
[6] Moreno J C, Prasath V B S, Neves J C. Color image pro-cessing by vectorial total variation with gradient channels coupling[J]. Inverse Problems & Imaging, 2016, 10(2): 461-497.
[7] Lu B B, Li Y, Wang Y M, et al. Gradient guided higher-order model based on Riemann geometry for color image denoising[J]. Journal of Image and Graphics, 2017, 22(10): 1335-1347．芦碧波, 李阳, 王永茂, 等. 梯度引导的高阶几何彩色图像去噪模型[J]. 中国图象图形学报, 2017, 22(10): 1335-1347.
[8] Radlak K, Malinski L, Smolka B. Deep learning for impul-sive noise removal in color digital images[C]//Proceedings of the Real-Time Image Processing and Deep Learning, Bal-timore, May 14, 2019. San Francisco: SPIE, 2019: 1099608.
[9] Jia J, Chen L. Using normal inverse Gaussian model for im-age denoising in NSCT domain[J]. Acta Electronica Sinica, 2011, 39(7): 1563-1568.贾建, 陈莉. 基于正态逆高斯模型的非下采样Contourlet变换图像去噪[J]. 电子学报, 2011, 39(7): 1563-1568.
[10] Liu S Q, Hu S H, Xiao Y. Shearlet domain SAR image de-noising via sparse representation[J]. Journal of Electronics & Information Technology, 2012, 34(9): 2110-2115.刘帅奇, 胡绍海, 肖扬. 基于稀疏表示的Shearlet域SAR图像去噪[J]. 电子与信息学报, 2012, 34(9): 2110-2115.
[11] Wang Z W, Li S Z. Adaptive fractal-wavelet image denois-ing base on multivariate statistical model[J]. Chinese Jour-nal of Computers, 2014, 37(6): 1380-1389.王智文, 李绍滋. 基于多元统计模型的分形小波自适应图像去噪[J]. 计算机学报, 2014, 37(6): 1380-1389.
[12] Wang X H, Zhu Y H, Lv F, et al. Cauchy distribution NSST- HMT model and its applications in image denoising[J]. Chinese Journal of Computers, 2018, 41(11): 78-90.王相海, 朱毅欢, 吕芳, 等. 基于Cauchy分布的非下采样Shearlet HMT模型及其图像去噪应用[J]. 计算机学报, 2018, 41(11): 78-90.
[13] Ji J, Li X, Xu S X, et al. SAR image despeckling by sparse reconstruction based on shearlets[J]. Acta Automatica Sinica, 2015, 41(8): 1495-1501.
[14] Jiao L L. An image denoising algorithm for strong noise image based on structural similarity of contourlet domain via grey relational analysis[C]//Proceedings of the 13th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, Sydney, Jul 3-5, 2019. Berlin, Hei-delberg: Springer, 2019: 300-309.
[15] Easley G, Labate D, Lim W Q. Sparse directional image re-presentations using the discrete shearlet transform[J]. Applied and Computational Harmonic Analysis, 2008, 25(1): 25-46.
[16] Mairal J, Bach F R, Ponce J, et al. Online dictionary learn-ing for sparse coding[C]//Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, Jun 14-18, 2009. New York: ACM, 2009: 689-696.
[17] Keerthi S S, Shevade S. A fast tracking algorithm for gene-ralized LARS/LASSO[J]. IEEE Transactions on Neural Net-works, 2007, 18(6): 1826-1830.
[18] Yang G Y. Image quality assessment and its application in image denoising[D]. Wuhan: Wuhan University, 2018.杨光义. 图像质量评价及其在图像去噪中的应用研究[D]. 武汉: 武汉大学, 2018.
[19] Zeng G P. Researeh on image denoising based on wavelet transform[D]. Beijing: Beijing Jiaotong University, 2007.曾国平. 基于小波变换的图像去噪算法研究[D]. 北京: 北京交通大学, 2007．
[20] Zhang Q. Research on image fusion and denoising algori-thms based on nonsubsampled Shearlet transforms domain[D]. Hefei: Hefei University of Technology, 2014.张强. 基于非下采样Shearlet变换域的图像融合及去噪算法研究[D]. 合肥: 合肥工业大学, 2014.
[21] Hu H Z, Sun H, Deng C Z, et al. Image de-noising algori-thm based on Shearlet transform[J]. Journal of Computer Applications, 2010, 30(6): 1562-1564.胡海智, 孙辉, 邓承志, 等. 基于Shearlet变换的图像去噪算法[J]. 计算机应用, 2010, 30(6): 1562-1564.