Improved Homomorphic Filtering and Multi-scale Fusion Method for Underwater Image Enhancement
-
摘要: 由于水体环境中光的吸收和散射，导致采集的水下图像存在色偏、对比度差、细节模糊以及光照不均的缺陷。针对以上缺陷，提出改进的同态滤波与多尺度融合的水下图像增强方法。首先，对采集的水下图像使用色彩平衡算法得到颜色校正的图像；然后，对颜色校正的图像分别采用CLAHE算法和改进的同态滤波算法得到对比度增强的图像和亮度均匀的图像；最后，对上文处理后具有优势特征的3张图像使用拉普拉斯对比度、局部对比度、显著性和饱和度这4个权重进行多尺度融合。为验证本文算法的有效性，采用主观视觉效果和3种客观指标进行验证。结果表明，本文算法不但可以解决颜色失真问题，而且能有效改善图像对比度、清晰度和亮度。Abstract: Due to the absorption and scattering of light in the water environment, the collected underwater image has many defects of color deviation, poor contrast, blurred details and uneven illumination. Therefore, an improved homomorphic filtering and multi-scale fusion method for underwater image enhancement is proposed to resolve this problem. Firstly, the color correction image is obtained by using color balance algorithm. Secondly, the contrast-limited adaptive histogram equalization(CLAHE) algorithm and the improved homomorphic filtering algorithm are respectively used for the color-corrected image to obtain a contrast-enhanced image with uniform brightness. Finally, the four weights of Laplacian contrast, local contrast, saliency and saturation were used for multi-scale fusion of the three images with dominant features after the above processing. In order to verify the effectiveness of the improved algorithm in this paper, subjective visual effects and three objective indicators are used for verification. The results show that this improved algorithm can not only solve the problem of color distortion, but also effectively improve the contrast, clarity and brightness of the image.
-
Key words:
- multi-scale fusion /
- color balance /
- CLAHE /
- homomorphic filtering
-
表 1 水下图像质量评价
图像 算法 MSE PSNR UIQM 图 6 原图 4 049.08 12.05 4.08 文献[4] 4 504.82 11.60 3.40 文献[7] 4 169.75 11.93 3.69 文献[8] 1 969.31 15.19 5.08 文献[9] 2 263.23 14.58 4.78 文献[10] 236.00 24.40 5.04 文献[11] 5 145.32 11.02 4.76 本文算法 580.53 20.49 5.17 图 7 原图 2 979.99 13.39 3.93 文献[4] 5 158.42 11.01 3.47 文献[7] 3 803.48 12.33 4.54 文献[8] 1 282.91 17.05 3.45 文献[9] 2 117.51 14.87 4.80 文献[10] 622.37 20.19 4.68 文献[11] 4 191.31 11.91 4.67 本文算法 945.12 18.38 5.00 图 8 原图 2 451.89 14.24 3.69 文献[4] 2 367.18 14.39 4.32 文献[7] 4 255.60 11.74 4.30 文献[8] 729.103 19.50 4.47 文献[9] 362.69 22.54 4.68 文献[10] 200.80 25.10 4.80 文献[11] 1 337.87 16.87 4.49 本文算法 285.12 23.58 4.83 图 9 原图 2 986.75 13.38 2.13 文献[4] 3 635.61 12.53 2.79 文献[7] 3 548.23 12.6307 4.08 文献[8] 1 155.63 17.50 3.24 文献[9] 1 161.26 17.48 3.12 文献[10] 232.51 24.47 3.99 文献[11] 1 894.88 15.36 3.05 本文算法 643.43 20.05 4.17 图 10 原图 5 568.17 10.67 4.25 文献[4] 7 163.31 9.58 4.75 文献[7] 12736.53 7.08 4.02 文献[8] 935.05 18.42 4.73 文献[9] 876.23 18.70 4.56 文献[10] 243.77 24.26 5.05 文献[11] 1 154.26 17.51 4.63 本文算法 726.12 19.52 5.18 
下载: 导出CSV
-
[1] 杨爱萍, 杨炳旺, 曲畅, 等. 基于透射率融合与优化的水下图像复原[J]. 天津大学学报(自然科学与工程技术版), 2019, 52(10): 1033-1044 https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX201910005.htmYANG A P, YANG B W, QU C, et al. Transmission fusion and optimization for single underwater image restoration[J]. Journal of Tianjin University (Science and Technology), 2019, 52(10): 1033-1044 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX201910005.htm [2] 李黎, 王惠刚, 刘星. 基于改进暗原色先验和颜色校正的水下图像增强[J]. 光学学报, 2017, 37(12): 1211003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201712020.htmLI L, WANG H G, LIU X. Underwater image enhancement based on improved dark channel prior and color correction[J]. Acta Optica Sinica, 2017, 37(12): 1211003 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201712020.htm [3] PAN P W, YUAN F, CHENG E. De-scattering and edge-enhancement algorithms for underwater image restoration[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(6): 862-871 [4] HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353 doi: 10.1109/TPAMI.2010.168 [5] GALDRAN A, PARDO D, PICÓN A, et al. Automatic red-channel underwater image restoration[J]. Journal of Visual Communication and Image Representation, 2015, 26: 132-145 doi: 10.1016/j.jvcir.2014.11.006 [6] 代成刚, 林明星, 王震, 等. 基于亮通道色彩补偿与融合的水下图像增强[J]. 光学学报, 2018, 38(11): 1110003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htmDAI C G, LIN M X, WANG Z, et al. Color compensation based on bright channel and fusion for underwater image enhancement[J]. Acta Optica Sinica, 2018, 38(11): 1110003 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201811011.htm [7] WEN H C, TIAN Y H, HUANG T J, et al. Single underwater image enhancement with a new optical model[C]//2013 IEEE International Symposium on Circuits and Systems (ISCAS). Beijing: IEEE, 2013: 753-756 [8] IQBAL K, ODETAYO M, JAMES A, et al. Enhancing the low quality images using unsupervised colour correction method[C]//2010 IEEE International Conference on Systems, Man and Cybernetics. Istanbul: IEEE, 2010: 1703-1709 [9] ANCUTI C, ANCUTI C O, HABER T, et al. Enhancing underwater images and videos by fusion[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012: 81-88 [10] GHANI A S A, ISA N A M. Underwater image quality enhancement through composition of dual-intensity images and Rayleigh-stretching[J]. SpringerPlus, 2014, 3: 757 doi: 10.1186/2193-1801-3-757 [11] IQBAL K, SALAM R A, OSMAN A, et al. Underwater image enhancement using an integrated colour model[J]. IAENG International Journal of Computer Science, 2007, 34(2): 239-244 [12] MCGLAMERY B L. A computer model for underwater camera systems[C]//Proceedings of SPIE 0208, Ocean Optics VI. Monterey: SPIE, 1980 [13] LIMARE N, LISANI J L, MOREL J M, et al. Simplest color balance[J]. Image Processing on Line, 2011, 1: 297-315 doi: 10.5201/ipol.2011.llmps-scb [14] ANCUTI C O, ANCUTI C, DE VLEESCHOUWER C, et al. Color balance and fusion for underwater image enhancement[J]. IEEE Transactions on Image Processing, 2018, 27(1): 379-393 doi: 10.1109/TIP.2017.2759252 [15] 林森, 迟凯晨, 李文涛, 等. 基于优势特征图像融合的水下光学图像增强[J]. 光子学报, 2020, 49(3): 0310003 https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202003025.htmLIN S, CHI K C, LI W T, et al. Underwater optical image enhancement based on dominant feature image fusion[J]. Acta Photonica Sinica, 2020, 49(3): 0310003 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202003025.htm [16] 孙杰. 基于图像融合的水下图像清晰化方法[J]. 兵器装备工程学报, 2019, 40(9): 193-197 doi: 10.11809/bqzbgcxb2019.09.040SUN J. Underwater image clearness method based on image fusion[J]. Journal of Ordnance Equipment Engineering, 2019, 40(9): 193-197 (in Chinese) doi: 10.11809/bqzbgcxb2019.09.040 -
点击查看大图
图(13) / 表(1)
计量
- 文章访问数: 129
- HTML全文浏览量: 91
- PDF下载量: 20
- 被引次数: 0
