为提升船舶实效图像视觉质量，提出基于视觉传达技术的船舶实效图像自适应增强方法。将获取的低分辨率船舶实效图像转换至HSI空间内，利用伽马校正技术自适应修正图像的亮度分量，得到亮度分布均匀的船舶实效图像；利用改进后的粒子群算法自适应地寻找Retinex算法中的高斯环绕尺度最优值，并在寻优过程中，针对船舶实效图像内容模糊以及对比度低等特点，将图像信息熵和标准差作为判断船舶实效图像质量的指标，建立粒子适应度函数，保证寻优结果对于处理低分辨率船舶实效图像可以达到更好的效果；利用优化后的Retinex算法，去除光照分量对船舶实效图像质量产生的不良影响，得到能反映出图像本质属性的增强图像。实验证明，利用该方法能够极大地提升船舶实效图像分辨率，增强后的图像清晰度高，无曝光点，细节丰富，达到了较好的视觉效果，可以为船舶实效图像的后期应用提供有利支撑。
This paper proposes an adaptive enhancement method of ship effective image based on visual communication technology to improve the visual quality of ship effective image and lay a foundation for the subsequent application of ship image. The low-resolution ship effective image was converted into HSI space, and the brightness component of the image was adaptively corrected by gamma correction technology to obtain the ship effective image with uniform brightness distribution. The improved particle swarm optimization algorithm is used to find the optimal value of Gaussian surround scale in Retinex algorithm adaptively. In the process of optimization, image information entropy and standard deviation are used as indicators to judge the quality of ship effective image, and particle fitness functions are established, aiming at the features of fuzzy content and low contrast of ship effective image. To ensure that the optimization results can achieve better results in the processing of low resolution ship images. Finally, the optimized Retinex algorithm was used to remove the adverse effects of light component on the effective ship image quality, and the enhanced image reflecting the essential attributes of the image was obtained. Experimental results show that this method can greatly improve the resolution of effective ship image, and the enhanced image has high resolution, no exposure point and rich details, so as to achieve a good visual effect, which can provide favorable support for the later application of effective ship image.
2023,45(12): 164-167 收稿日期：2023-01-29
DOI：10.3404/j.issn.1672-7619.2023.12.033
分类号：TP391
作者简介：傅建明(1978-),男,硕士,副教授,研究方向为艺术设计
参考文献：
[1] 曾广淼, 俞万能, 王荣杰, 等. 船舶目标重叠下马赛克图像数据增强方法研究[J]. 控制理论与应用, 2022, 39(6): 1139–1148
ZENG Guangmiao, YU Wanneng, WANG Rongjie, et al. Research on mosaic image data enhancement and detection method for overlapping ship targets[J]. Control Theory & Applications, 2022, 39(6): 1139–1148
[2] 常戬, 贺春泽, 董育理, 等. 改进双边滤波和阈值函数的图像增强算法[J]. 计算机工程与应用, 2020, 56(3): 207–213
Changjian, He Chunze, DONG Yuli, et al. Improved Image Enhancement Algorithm for Bilateral Filtering and Threshold Function[J]. Computer Engineering and Applications, 2020, 56(3): 207–213
[3] 于希明, 洪硕, 于金祥, 等. 可见光遥感图像船舶目标数据增强方法研究[J]. 仪器仪表学报, 2020, 41(11): 261–269
YU Ximing, HONG Shuo, YU Jinxiang, et al. Research on a ship target data augmentation method of visible remote sensing image[J]. Chinese Journal of Scientific Instrument, 2020, 41(11): 261–269
[4] 林昌, 周海峰, 陈武. 基于双边滤波的高斯金字塔变换Retinex图像增强算法[J]. 激光与光电子学进展, 2020, 57(16): 209–215
LIN Chang, ZHOU Haifeng, CHEN Wu. Gaussian Pyramid Transform Retinex Image Enhancement Algorithm Based on Bilateral Filtering[J]. Laser & Optoelectronics Progress, 2020, 57(16): 209–215
[5] 黄宁淑. 视觉传达技术的雾天舰船图像恢复研究[J]. 舰船科学技术, 2021, 43(14): 184–186
HUANG Ningshu. Research on ship image restoration in fog with visual communication technology[J]. Ship Science and Technology, 2021, 43(14): 184–186
[6] 成藻. 基于视觉传达技术的低分辨率舰船图像优化[J]. 舰船科学技术, 2021, 43(24): 190–192
CHENG Zao. Research on low resolution ship image optimization based on visual communication technology[J]. Ship Science and Technology, 2021, 43(24): 190–192
