计算机工程 ›› 2020, Vol. 46 ›› Issue (7): 235-242.doi: 10.19678/j.issn.1000-3428.0055324

• 图形图像处理 • 上一篇    下一篇

基于人类视觉系统的水下图像质量评价方法

赵馨, 侯国家, 潘振宽, 李景明, 王国栋   

  1. 青岛大学 计算机科学技术学院, 山东 青岛 266071
  • 收稿日期:2019-06-28 修回日期:2019-08-19 发布日期:2019-08-28
  • 作者简介:赵馨(1993-),女,硕士研究生,主研方向为图像处理;侯国家(通信作者),讲师、博士;潘振宽,教授、博士;李景明,硕士研究生;王国栋,副教授、博士。
  • 基金项目:
    国家自然科学基金(61901240);中国国家留学基金(201908370002);中国博士后科学基金面上项目(2017M612204);山东省自然科学基金(ZR2019BF042,ZR2019MF050)。

Underwater Image Quality Assessment Method Based on Human Vision System

ZHAO Xin, HOU Guojia, PAN Zhenkuan, LI Jingming, WANG Guodong   

  1. College of Computer Science and Technology, Qingdao University, Qingdao, Shandong 266071, China
  • Received:2019-06-28 Revised:2019-08-19 Published:2019-08-28

摘要: 目前水下图像质量评价方法虽然准确性较高,但与人类主观评价相关性较低,难以实现高质量的评价。针对该问题,提出一种基于人类视觉系统进行水下图像质量评价的UIQA方法。将基于CIELab表色系的色彩饱和度、基于暗通道理论的亮度对比度和图像清晰度3个测量分量进行线性组合,来评价不同场景的水下图像质量,并将评价结果与采用UIQM方法和UCIQE方法得到的结果进行对比。实验结果表明,与UIQM方法和UCIQE方法相比,采用UIQA方法得到的水下图像质量评价结果与主观评价结果具有高度一致性,与人类主观评价相关性更高。

关键词: 水下图像质量, 色彩饱和度, 亮度对比度, 清晰度, 人类主观评价

Abstract: Despite the high accuracy of existing underwater image quality assessment methods,they have weak correlation with subjective assessment of human beings,so it is difficult to achieve high-quality evaluation.To address the problem,this paper proposes an Underwater Image Quality Assessment(UIQA) method based on the human vision system.The method makes linear combinations of color saturation based on CIELab surface color system,brightness contrast based on dark channel theory,and image sharpness,so as to evaluate the underwater image quality in different scenes.The evaluation results are compared with those obtained by the UIQM method and UCIQE method.Experimental results show that compared with the quality assessment results of underwater images obtained by UIQM method and UCIQE method,those obtained by the UIQA method are highly consistent with the subjective evaluation results and have higher correlation with subjective evaluation of human beings.

Key words: underwater image quality, color saturation, brightness contrast, sharpness, subjective assessment of human beings

中图分类号: