Adaptive Retinex Algorithm Based on Detail Selection Used in Underwater Image Enhancement

doi:10.3778/j.issn.1002-8331.2009-0497

Abstract

Abstract: Aiming at the contradiction of color distortion and image detail enhancement when Retinex algorithm is applied to underwater image enhancement, the adaptive multi-scale Retinex underwater image enhancement algorithm combined with detail information is proposed in this paper. The selection requirements of the scale of convolution function in the enhancement of Retinex algorithm for underwater images containing different detail information are analyzed. Image gradient is used as the adjustment factor to adaptively adjust the weight of multi-scale Retinex operator, which is used to meet the requirements of underwater image with different detail information for contrast enhancement, and effectively alleviate the contradiction between color distortion and detail contrast enhancement in underwater image enhancement. Several groups of experiments show that the algorithm is superior to the traditional multi-scale（MSR） and multi-scale Retinex with color restoration（MSRCR） in removing the blue-green background of underwater image, avoiding color distortion, eliminating non-uniform illumination and image detail enhancement.

Key words: underwater image enhancement, Retinex, multi-scale Retinex（MSR）, adaptive multi-scale Retinex（AMSR）, image gradient

摘要： 针对Retinex算法应用于水下图像增强中，常出现颜色失真与图像细节增强相矛盾的现象，提出了结合细节信息的自适应多尺度Retinex水下图像增强算法。分析包含不同细节信息的水下图像对Retinex算法增强中卷积函数尺度大小的选择要求；采用图像梯度作为调节因子，自适应调整多尺度Retinex算子的权重，用于适应包含不同细节信息的水下图像对对比度增强的要求，有效地缓和了水下图像增强在颜色失真和细节对比度提升之间的矛盾。多组实验验证了该算法在去除水下图像的蓝绿背景、避免颜色失真、消除非均匀光照和图像细节增强等方面均优于传统多尺度和颜色保真的多尺度Retinex算法。

关键词: 水下图像增强, Retinex算法, 多尺度Retinex算法, 自适应多尺度Retinex算法, 图像梯度

XU Li, LU Guiming, QIU Zhenguang. Adaptive Retinex Algorithm Based on Detail Selection Used in Underwater Image Enhancement[J]. Computer Engineering and Applications, 2022, 58(11): 224-233.

许丽, 陆桂明, 邱贞光. 结合细节信息的自适应Retinex算法水下图像增强[J]. 计算机工程与应用, 2022, 58(11): 224-233.

References

[1] 范素芳.坝堤渗漏监测关键技术及方法研究[D].湘潭：湖南科技大学，2012.
FAN S F.Research on the key technology and methods of dike leakage monitoring[D].Xiangtan：Hunan University of Science and Technology，2012.
[2] 王金龙，何仁洋，张海彬，等.海底管道检测最新技术及发展方向[J].石油机械，2016，44（10）：112-118.
WANG J L，HE R Y，ZHANG H B，et al.State-of-the-art advancement and development direction of submarine pipeline technology[J].China Petroleum Machinery，2016，44（10）：112-118.
[3] 陈志远.复杂海域下三维地形生成及路径规划方法研究[D].哈尔滨：哈尔滨工程大学，2015.
CHEN Z Y.Three-dimensional terrain generation and research on path planning method in complex seabed[D].Harbin：Harbin Engineering University，2015.
[4] 徐玉如，李彭超.水下机器人发展趋势[J].自然杂志，2011，33（3）：125-131.
XU Y R，LI P C.Developing tendency of unmanned underwater vehicles[J].Chinese Journal of Nature，2011，33（3）：125-131.
[5] BIAGI M.Image processing based transceiver design for acoustic PPM underwater links[J].IEEE Journal of Oceanic Engineering，2014，39（4）：592-606.
[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.
[7] 赵欣慰，金韬，池灏，等.不同光照条件下水下成像背景光的建模与研究[J].物理学报，2015，64（10）：110-118.
ZHAO X W，JIN T，CHI H，et al.Modeling and simulation of the background light in underwater imaging under different illumination conditions[J].Acta Physica Sinica，2015，64（10）：110-118.
[8] 王永鑫，刁鸣，韩闯.基于迭代直方图均衡化的常规光源下水下成像增强算法[J].光子学报，2018，47（11）：97-107.
WANG Y X，DIAO M，HAN C.Underwater image enhancement algorithm based on iterative histogram equalization with conventional light source[J].Acta Photonica Sinica，2018，47（11）：97-107.
[9] 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 D M，WANG Y，SONG W，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.
[10] 谢昊伶，彭国华，王凡，等.基于背景光估计与暗通道先验的水下图像复原[J].光学学报，2018，38（1）：18-27.
XIE H L，PENG G H，WANG F，et al.Underwater image restoration based on background light estimation and dark channel prior[J].Acta Optica Sinica，2018，38（1）：18-27.
[11] 黄松，易本顺.基于自适应透射率比的水下图像复原算法[J].浙江大学学报（工学版），2018，52（1）：166-173.
HUANG S，YI B S.Underwater image restoration algorithm based on adaptive transmission ratio[J].Journal of Zhejiang University（Engineering Science），2018，52（1）：166-173.
[12] 宋巍，王龑，黄冬梅，等.结合背景光融合及水下暗通道先验和色彩平衡的水下图像增强[J].模式识别与人工智能，2018，31（9）：856-868.
SONG W，WANG Y，HUANG D M，et al.Combining background light fusion and underwater dark channel prior with color balancing for underwater image enhancement[J].Pattern Recognition and Artificial Intelligence，2018，31（9）：856-868.
[13] Alex R S M，SUPRIYA M.Underwater image enhancement using single scale Retinex on a recon?gurable hardware[C]//IEEE International Symposium on Ocean Electronics（SYMPOL），2015：1-5.
[14] ZHANG S，WANG T，DONG J Y，et al.Underwater image enhancement via extended multi-scale Retinex[J].Neurocomputing，2017，245：1-9.
[15] 石磊，奚茂龙，孙俊.基于可控核双边滤波Retinex水下图像增强算法[J].量子电子学报，2018，35（1）：7-12.
SHI L，XI M L，SUN J.Underwater image enhancement algorithm based on controllable nuclear bilateral filtering Retinex[J].Chinese Journal of Quantum Electronics，2018，35（1）：7-12.
[16] LAND E，MCCANN J.Lightness and Retinex theory[J].Journal of the Optical of America，1971，61（1）：1-11.
[17] JOBSON D J，RAHMAN Z，WOODELL G.A multiscale Retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing，1997，6（7）：965-976.
[18] AL-AMEEN Z，SULONG G.A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex[J].Scanning，2015，37（2）：116-125.
[19] RAHMAN Z.Investigating the relationship between image enhancement and image compression in the context of the multi-scale Retinex[J].Journal of Visual Communication and Image Representation，2011，22（3）：237-250.
[20] 黄允浒，吐尔洪江·阿布都克力木，刘芳园，等.多尺度Retinex算法与其他图像增强方法比较[J].新疆师范大学学报（自然科学版），2017，36（2）：69-77.
HUANG Y H，TURGHUNJAN A，LIU F Y，et al.Comparison of multi-scale Retinex algorithm and other image enhancement methods[J].Journal of Xinjiang Normal University，2017，36（2）：69-77.