基于非抽样双树-复小波变换与模糊聚类的声呐图像去噪技术

doi:10.1007/s12204-023-2662-3

摘要/Abstract

摘要： 由成像声呐设备通过接收物体回波生成声呐图像常伴随严重的斑点噪声，导致图像失真、信息丢失等。常用光学去噪方法去除声呐图像中斑点噪声效果不佳，会降低图像视觉效果。为解决上述不足，提出了一种基于模糊聚类与非抽样双树复小波变换的声呐图像去噪方法。该方法在分解图像时提供完美的平移不变性和改进的方向选择特性，将噪声和边缘在高频系数中表现更丰富；模糊聚类能够根据斑点噪声的幅值特性，实现噪声与有效信息的分离，保留有效信息，实现了去除噪声的目标；同时通过双边滤波平滑低频系数，提高图像视觉效果。为了验证算法的有效性，进行了多组消融实验，并使用不同方差的斑点声呐图像进行了评估，与现有的变换域中去斑方法相比。实验结果表明：该方法能够有效地改善图像质量；处理后的图像视觉效果得到提升，尤其是在噪声严重的情况下，去噪性能依然拥有较好的效果。

关键词: 模糊聚类, 双边滤波, 非抽样双树, 复小波变换, 图像去噪

Abstract: Imaging sonar devices generate sonar images by receiving echoes from objects, which are often accompanied by severe speckle noise, resulting in image distortion and information loss. Common optical denoising methods do not work well in removing speckle noise from sonar images and may even reduce their visual quality. To address this issue, a sonar image denoising method based on fuzzy clustering and the undecimated dual-tree complex wavelet transform is proposed. This method provides a perfect translation invariance and an improved directional selectivity during image decomposition, leading to richer representation of noise and edges in high frequency coefficients. Fuzzy clustering can separate noise from useful information according to the amplitude characteristics of speckle noise, preserving the latter and achieving the goal of noise removal. Additionally, the low frequency coefficients are smoothed using bilateral filtering to improve the visual quality of the image. To verify the effectiveness of the algorithm, multiple groups of ablation experiments were conducted, and speckle sonar images with different variances were evaluated and compared with existing speckle removal methods in the transform domain. The experimental results show that the proposed method can effectively improve image quality, especially in cases of severe noise, where it still achieves a good denoising performance.

中图分类号:

TP391

. 基于非抽样双树-复小波变换与模糊聚类的声呐图像去噪技术[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 998-1008.

LIU Biao, LIU Guangyu, FENG Wei, WANG Shuai, ZHOU Bao, ZHAO Enming. Undecimated Dual-Tree Complex Wavelet Transform and Fuzzy Clustering-Based Sonar Image Denoising Technique[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 998-1008.

参考文献

[1] WANG C J, SHEN L R, FAN Y S, et al. Sonar image denoising based on anisotropic guided filtering [C]//2022 5th International Conference on Intelligent Autonomous Systems. Dalian: IEEE, 2022: 54-59.

[2] LIU G Y, ZENG Z Y, CAO Y, et al. Sonar image denoising based on density clustering and gray scale transformation in NSST domain [J]. Journal of Hunan University (Natural Sciences), 2022, 49(8): 186-195 (in Chinese).

[3] LI F, ZHU L L. Comparative research on denoising effects of common filtering algorithms based on sonar image [J]. Mine Warfare & Ship Self-Defence, 2017, 25(4): 82-86 (in Chinese).

[4] CHEN Y, XU H L, XING Q, et al. A denoising algorithm for SICM image based on wavelet and bilateral filtering [J]. Electronic Measurement Technology, 2022, 45(4): 114-119 (in Chinese).

[5] KOLLEM S, REDDY K R, RAO D S. Improved partial differential equation-based total variation approach to non-subsampled contourlet transform for medical image denoising [J]. Multimedia Tools and Applications, 2021, 80(2): 2663-2689.

[6] ROUTRAY S, MALLA P P, SHARMA S K, et al. A new image denoising framework using bilateral filtering based non-subsampled shearlet transform [J]. Optik, 2020, 216: 164903.

[7] WANG L Y, CHEN J Y. Image denoising based on dual tree complex wavelet transform and bilateral filter [J]. Journal of Huazhong Normal University (Natural Sciences), 2021, 55(6): 1030-1036 (in Chinese).

[8] ZHANG Y L. Improving denoising algorithm for fuzzy clustering-based wavelet transform image [J]. Computer Applications and Software, 2010, 27(8): 133-135 (in Chinese).

[9] KINGSBURY N. The dual-tree complex wavelet transform: A new efficient tool for image restoration and enhancement [C]//9th European Signal Processing Conference. Rhodes: IEEE, 1998: 1-4.

[10] HILL P R, ANANTRASIRICHAI N, ACHIM A, et al. Undecimated dual-tree complex wavelet transforms [J]. Signal Processing: Image Communication, 2015, 35: 61-70.

[11] YANG P, YANG G W. Bivariate shrinkage using undecimated dual-tree complex wavelet transform for image denoising [J]. Journal of Intelligent & Fuzzy Systems, 2016, 30(6): 3111-3122.

[12] WU J N, SHI M H, XING Z. Image denoising using magnitude-phase of the undecimated dual-tree complex wavelet transform [J]. Infrared Technology, 2018, 40(7): 647-653 (in Chinese).

[13] SAEEDZARANDI M, NEZAMABADI-POUR H, SARYAZDI S, et al. Image denoising in undecimated dual-tree complex wavelet domain using multivariate t-distribution [J]. Multimedia Tools and Applications, 2020, 79(31/32): 22447-22471.

[14] FARHADIANI R, HOMAYOUNI S, SAFARI A. Hybrid SAR speckle reduction using complex wavelet shrinkage and non-local PCA-based filtering [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(5): 1489-1496.

[15] HE X W, SUN Y, WEI X, et al. Denoising algorithm of cerenkov luminescence images based on spatial information improved clustering [J]. Acta Optica Sinica, 2018, 38(10): 1017001.

[16] WANG H Q, LÜ J Y, ZHANG W. GPR image denoising based on bilateral filtering BM3D algorithm[J]. Journal of Lanzhou University of Technology, 2022, 48(1): 91-97 (in Chinese).

[17] KARTHIKEYAN M, VIJAYARAGHAVAN V. Denoising of images using principal component analysis and undecimated dual tree complex wavelet transform [J]. International Journal of Biomedical Engineering and Technology, 2018, 26(3/4): 304.

[18] WANG X H, ZHOU Y, ZHOU Y. Infrared and visible image fusion in undecimated dual-tree complex wavelet domain [J]. Computer Engineering and Design, 2017, 38(3): 729-734 (in Chinese).

[19] HUANG Y F, LI W X, YUAN F. Speckle noise reduction in sonar image based on adaptive redundant dictionary [J]. Journal of Marine Science and Engineering, 2020, 8(10): 761.

[20] NIU H Q, WU J Z, XU J, et al. Denoising of infrared images of porcelain sleeve cable terminal considering inter-scale correlation [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(4): 15-21 (in Chinese).

[21] TANG W, JIA F X, WANG X M. Adaptive fusion of visible and infrared images based on bilateral filtering [J]. Acta Armamentarii, 2022, 43(11): 2836-2845 (in Chinese).

[22] XUE S Q, HE D D. Denoising algorithm for medical ultrasound image based on 2D-VMD and bilateral filtering [J]. Journal of Xi’an University of Science and Technology, 2021, 41(3): 516-523 (in Chinese).

[23] KAUR S, SINGH N. Image denoising techniques: a review[J]. International Journal of Innovative Research in Computer and Communication Engineering, 2014, 2(6): 4578-4583.

[24] LIU G Y, BIAN H Y, SHEN Z Y, et al. Research on spectral clustering met algorithm of sonar image denoising in morphological wavelet domain [J]. Transducer and Microsystem Technologies, 2011, 30(10): 41-43 (in Chinese).

[25] BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 60-65.