• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Liu, Yutao (Liu, Yutao.) | Gu, Ke (Gu, Ke.) (学者:顾锞) | Cao, Jingchao (Cao, Jingchao.) | Wang, Shiqi (Wang, Shiqi.) | Zhai, Guangtao (Zhai, Guangtao.) | Dong, Junyu (Dong, Junyu.) | Kwong, Sam (Kwong, Sam.)

收录:

EI Scopus SCIE

摘要:

Due to the light absorption and scattering in waterbodies, acquired underwater images frequently suffer from color cast, blur, low contrast, noise, etc., which seriously degrade the image quality and affect their subsequent applications. Therefore, it is necessary to propose a reliable and practical underwater image quality assessment (IQA) model that can faithfully evaluate underwater image quality. To this end, in this article, we establish a novel quality assessment model for underwater images by in-depth analysis and characterization of multiple image properties. Specifically, we propose characterizing the image luminance, color cast, sharpness, contrast, fog density and noise to comprehensively describe the image quality to evaluate the underwater image quality more accurately. Dedicated features are elaborately investigated to characterize those quality-aware image properties. After feature extraction, we employ support vector regression (SVR) to integrate all the quality-aware features and regress them onto the underwater image quality score. Extensive tests performed on standard underwater image quality databases demonstrate the superior prediction performance of the proposed underwater IQA model to state-of-the-art congeneric quality assessment models.

关键词:

Underwater image objective metric Image color analysis Colored noise Predictive models no-reference (NR) Visualization image quality assessment (IQA) Feature extraction Image quality statistical modeling Indexes

作者机构:

  • [ 1 ] [Liu, Yutao]Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China
  • [ 2 ] [Cao, Jingchao]Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China
  • [ 3 ] [Dong, Junyu]Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China
  • [ 4 ] [Gu, Ke]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Wang, Shiqi]City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
  • [ 6 ] [Kwong, Sam]City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
  • [ 7 ] [Zhai, Guangtao]Shanghai Jiao Tong Univ, Inst Image Commun & Informat Proc, Shanghai 200240, Peoples R China

通讯作者信息:

  • [Cao, Jingchao]Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China;;[Dong, Junyu]Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China;;

查看成果更多字段

相关关键词:

来源 :

IEEE TRANSACTIONS ON MULTIMEDIA

ISSN: 1520-9210

年份: 2024

卷: 26

页码: 2560-2573

7 . 3 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 20

ESI高被引论文在榜: 4 展开所有

  • 2024-11
  • 2024-11
  • 2024-9
  • 2024-9

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:574/4963737
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司