Research on underwater image detail enhancement based on unsharp mask guided filtering
-
摘要: 针对水下图像对比度偏低，细节模糊的问题，本文提出基于非锐化掩模引导滤波的细节增强方法。首先由原始图像做引导图进行滤波得到细节层图像，并对细节层使用噪声检测的中值滤波去除斑点噪声；然后对原始图像进行基于均值滤波的非锐化掩模，得到锐化图像，并将锐化图像作为引导图对原始图像进行引导滤波，获取基础层图像；最后将滤波后的细节层进行增益后与引导滤波获取的基础层进行叠加，达到增强水下图像细节的目的。并通过信息熵、局部对比度和平均梯度3种客观评价指标对图像处理结果进行了对比分析，主观和客观测试结果表明，本文采用的算法能够有效提高图像对比度以及增强细节信息，有利于提高水下图像资料解释的准确性。Abstract: To overcome the problem of the low contrast and blurred details of underwater images, we propose a method to enhance the details of underwater images based on unsharp mask guided filtering in this paper. Firstly, the original image is guided filtering to obtain a detail layer image, and the speckle noise in detail layer image is removed by the median filtering based on noise detection. Then the unsharp mask based on mean filtering is operated on the original image to obtain a sharpened image, which is used as guidance image to perform guided filtering on the original image, and the base layer image is obtained. It is magnified to boost the details so that the details of the output image are obtained. Finally, the filtered detail layer is magnified to boost the details, and the enhanced underwater image is the combination of the boosted detail layer and the base layer. The image processing results are compared and analyzed through three objective evaluation indexes: information entropy, local contrast and average gradient. Subjective and objective test results show that the proposed algorithm can effectively improve image contrast and detail information, which is beneficial to improve the accuracy of underwater image data interpretation.
-
Key words:
- underwater image /
- guided filtering /
- detail enhancement /
- unsharp mask
-
图 4 细节层滤波
a. 原始图像；b. 细节图像；c. 细节滤波图像
Fig. 4 Detail layer filtering
a. Original image；b. detail image；c. detail layer filtering image
图 5 非锐化掩模效果对比
a. 高斯滤波非锐化掩模；b. 均值滤波非锐化掩模
Fig. 5 Comparison of unsharp masking results
a. Gaussian filter unsharp mask; b. mean filter unsharp mask
表 1 原图和不同算法图像客观指标对比结果
Tab. 1 Contrast results of image objective indexes between original image and images with different algorithms
图像 指标 原图 CLAHE 引导滤波 DCP IDCP 本文算法 珊瑚 IE 6.594 4 7.112 0 7.045 1 6.684 4 7.043 7 7.047 9 LC 0.234 3 0.361 5 0.452 2 0.253 8 0.236 2 0.530 1 MG 33.862 6 52.346 6 55.933 2 35.456 1 49.950 5 60.670 0 鱼 IE 6.446 6 6.814 7 6.767 4 6.508 8 6.166 3 6.918 0 LC 0.259 8 0.373 3 0.441 9 0.302 3 0.175 0 0.528 6 MG 36.174 5 50.895 3 52.192 9 37.196 1 39.033 3 58.707 0 虾 IE 7.057 6 7.576 9 7.585 9 7.260 0 7.476 3 7.647 7 LC 0.216 6 0.335 3 0.406 3 0.280 3 0.229 3 0.488 2 MG 40.694 4 63.421 4 63.317 4 46.668 5 51.447 9 77.347 0 注：加粗数字表示每组数据的最优值。 
下载: 导出CSV
-
[1] 郭继昌, 李重仪, 郭春乐, 等. 水下图像增强和复原方法研究进展[J]. 中国图象图形学报, 2017, 22(3): 273−287.Guo Jichang, Li Chongyi, Guo Chunle, et al. Research progress of underwater image enhancement and restoration methods[J]. Journal of Image and Graphics, 2017, 22(3): 273−287. [2] 王建, 宋占杰, 李重仪, 等. 水下图像增强方法研究现状[J]. 海洋技术学报, 2016, 35(2): 76−82.Wang Jian, Song Zhanjie, Li Chongyi, et al. Research progress of underwater image enhancement methods[J]. Journal of Ocean Technology, 2016, 35(2): 76−82. [3] 路晓磊, 张丽婷, 王芳, 等. 海底声学探测技术装备综述[J]. 海洋开发与管理, 2018, 35(6): 91−94. doi: 10.3969/j.issn.1005-9857.2018.06.020Lu Xiaolei, Zhang Liting, Wang Fang, et al. Summary of submarine acoustic detection technology and equipment[J]. Ocean Development and Management, 2018, 35(6): 91−94. doi: 10.3969/j.issn.1005-9857.2018.06.020 [4] Schettini R, Corchs S. Underwater image processing: state of the art of restoration and image enhancement methods[J]. EURASIP Journal on Advances in Signal Processing, 2010: ID746052. [5] Garcia R, Nicosevici T, Cufí X. On the way to solve lighting problems in underwater imaging[C]//Ocean's 2002 Conference and Exhibition. Biloxi, MI, USA: IEEE, 2002: 1018−1024. [6] Jaffe J S. Underwater optical imaging: the past, the present, and the prospects[J]. IEEE Journal of Oceanic Engineering, 2015, 40(3): 683−700. doi: 10.1109/JOE.2014.2350751 [7] 黄冬梅, 王龑, 宋巍, 等. 不同颜色模型下自适应直方图拉伸的水下图像增强[J]. 中国图象图形学报, 2018, 23(5): 640−651.Huang Dongmei, Wang Yan, Song Wei, et al. Underwater image enhancement method using adaptive histogram stretching in different color models[J]. Journal of Image and Graphics, 2018, 23(5): 640−651. [8] Zuiderveld K. Contrast limited adaptive histogram equalization[M]//Graphics Gems IV. San Diego, CA, USA: Academic Press, 1994: 474−485. [9] 杨卫中, 徐银丽, 乔曦, 等. 基于对比度受限直方图均衡化的水下海参图像增强方法[J]. 农业工程学报, 2016, 32(6): 197−203. doi: 10.11975/j.issn.1002-6819.2016.06.027Yang Weizhong, Xu Yinli, Qiao Xi, et al. Method for image intensification of underwater sea cucumber based on contrast limited adaptive histogram equalization[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(6): 197−203. doi: 10.11975/j.issn.1002-6819.2016.06.027 [10] 陈从平, 王健, 邹雷, 等. 一种有效的低对比度水下图像增强算法[J]. 激光与红外, 2012, 42(5): 567−571. doi: 10.3969/j.issn.1001-5078.2012.05.020Chen Congping, Wang Jian, Zou Lei, et al. Effective enhancement algorithm for low contrast underwater images[J]. Laser & Infrared, 2012, 42(5): 567−571. doi: 10.3969/j.issn.1001-5078.2012.05.020 [11] Singh G, Jaggi N, Vasamsetti S, et al. Underwater image/video enhancement using wavelet based color correction (WBCC) method[C]//2015 IEEE Underwater Technology. Chennai, India: IEEE, 2015: 1−5. [12] He Kaiming, Sun Jian, Tang Xiaoou. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(12): 2341−2353. [13] Sahu P, Gupta N, Sharma N. A survey on underwater image enhancement techniques[J]. International Journal of Computer Applications, 2014, 87(13): 19−23. doi: 10.5120/15268-3743 [14] 曹美, 盛惠兴, 李庆武, 等. 基于暗原色先验模型的水下彩色图像增强算法[J]. 量子电子学报, 2016, 33(2): 140−147.Cao Mei, Sheng Huixing, Li Qingwu, et al. Underwater color image enhancement algorithm based on prior dark-channel model[J]. Chinese Journal of Quantum Electronics, 2016, 33(2): 140−147. [15] 朱振杰, 王红茹. 基于暗原色先验原理的水下图像增强[J]. 图学学报, 2018, 39(3): 453−462.Zhu Zhenjie, Wang Hongru. Underwater image enhancement based on the principle of dark channel prior[J]. Journal of Graphics, 2018, 39(3): 453−462. [16] Han Min, Chen Chao. Enhancing underwater image by dark channel prior and color correction[C]//2016 6th International Conference on Information Science & Technology. Dalian, China: IEEE, 2016: 505−510. [17] 汤忠强, 周波, 戴先中, 等. 基于改进DCP算法的水下机器人视觉增强[J]. 机器人, 2018, 40(2): 222−230.Tang Zhongqiang, Zhou Bo, Dai Xianzhong, et al. Underwater robot visual enhancements based on the improved DCP algorithm[J]. Robot, 2018, 40(2): 222−230. [18] He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(6): 1397−1409. [19] 谢岱伟. 红外图像细节增强算法研究及其FPGA实现[D]. 南京: 南京理工大学, 2016.Xie Daiwei. Research on infrared image detail enhancement algorithm and its FPGA implementation[D]. Nanjing: Nanjing University of Science & Technology, 2016. [20] 马学磊. 基于噪声点检测的中值滤波图像去噪算法[D]. 西安: 西安电子科技大学, 2008.Ma Xuelei. Median filtering image denoising algorithm based on noise pixel detection[D]. Xi’an: Xidian University, 2008. [21] 甘玲, 张倩雯. 结合NSCT与引导滤波的图像融合方法[J]. 红外技术, 2018, 40(5): 444−448, 454.Gan Ling, Zhang Qianwen. Image fusion method combining non-subsampled contourlet transform and guide filtering[J]. Infrared Technology, 2018, 40(5): 444−448, 454. [22] Wang Yang, Pan Zhibin. Image contrast enhancement using adjacent-blocks-based modification for local histogram equalization[J]. Infrared Physics & Technology, 2017, 86: 59−65. [23] Liu Jiahang, Zhou Chenghu, Chen Peng, et al. An efficient contrast enhancement method for remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1715−1719. doi: 10.1109/LGRS.2017.2730247 -
图(6) / 表(1)
计量
- 文章访问数: 380
- HTML全文浏览量: 160
- PDF下载量: 30
- 被引次数: 0
