计算机应用 ›› 2019, Vol. 39 ›› Issue (9): 2701-2706.DOI: 10.11772/j.issn.1001-9081.2019020302

• 虚拟现实与多媒体计算 • 上一篇    下一篇

基于TV-L1结构纹理分解的图像融合质量评价算法

张斌1, 罗晓清1, 张战成2   

  1. 1. 江南大学 物联网工程学院, 江苏 无锡 214122;
    2. 苏州科技大学 电子与信息工程学院, 江苏 苏州 215009
  • 收稿日期:2019-02-26 修回日期:2019-05-07 出版日期:2019-09-10 发布日期:2019-05-28
  • 通讯作者: 罗晓清
  • 作者简介:张斌(1994-),男,江西景德镇人,硕士研究生,主要研究方向:图像融合;罗晓清(1980-),女,江西南昌人,副教授,博士,CCF会员,主要研究方向:图像融合、医学图像分析;张战成(1977-),男,山西平遥人,副教授,博士,主要研究方向:图像融合、医学图像分析。
  • 基金资助:

    国家自然科学基金资助项目(61772237);中央高校基本科研业务费资助项目(JUSRP51618B);苏州市重点产业技术创新项目(SYG201702)。

Image fusion quality evaluation algorithm based on TV-L1 structure and texture decomposition

ZHANG Bin1, LUO Xiaoqing1, ZHANG Zhancheng2   

  1. 1. School of Internet of Things Engineering, Jiangnan University, Wuxi Jiangsu 214122, China;
    2. School of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou Jiangsu 215009, China
  • Received:2019-02-26 Revised:2019-05-07 Online:2019-09-10 Published:2019-05-28
  • Supported by:

    This work is partially supported by the National Natural Science Foundation of China (61772237), the Fundamental Research Funds for the Central Universities (JUSRP51618B), the Technological Innovation Projects of Major Industries in Suzhou City (SYG201702).

摘要:

为对图像融合算法进行客观准确的综合评价,提出一种基于总变差正则化(TV-L1)结构纹理分解的评价算法。根据对人类视觉系统的研究,可知人们对图像质量的感知主要来自图像底层视觉特征,而结构特征以及纹理特征是最重要的图像底层视觉特征,但目前的图像融合质量评价算法并没有利用这两种特征来进行评价。鉴于此,将图像进行二级结构和纹理分解,根据结构和纹理图像蕴含图像特征的不同,从结构图像和纹理图像两方面分别进行相似度评价,综合各级得分得到最终的评价总得分。基于30幅图像的数据集和8种主流融合算法,参照已有的11种客观评价指标,用波达计数法和肯德尔系数检验了该评价指标的一致性,另外在主观评价图像集上验证了该客观评价指标与主观评价的一致性。

关键词: 图像融合, 融合质量评价, 总变差正则化, 结构相似度, 结构和纹理分解

Abstract:

In order to objectively and accurately evaluate the image fusion algorithms, an evaluation algorithm based on TV-L1 (Total Variation regularization) structure and texture decomposition was proposed. According to the studies on human visual system, human's perception to image quality mainly comes from the underlying visual features of image, and structure features and texture features are the most important features of underlying visual feature of image. However, the existed image fusion quality evaluation algorithms ignore this fact and lead to inaccurate evaluation. To address this problem, a pair of source images and their corresponding fusion results were individually decomposed into structure and texture images with a two-level TV-L1 decomposition. Then, According to the difference of image features between the structure and texture images, the similarity evaluation was carried out from the decomposed structure image and the texture image respectively, and the final evaluation score was obtained by integrating the scores at all levels. Based on the dataset with 30 images and 8 mainstream fusion algorithms, compared with the 11 existing objective evaluation indexes, the Borda counting method and Kendall coefficient were employed to verify the consistency of the proposed evaluation algorithm. Moreover, the consistency between the proposed objective evaluation index and the subjective evaluation is verified on the subjective evaluation image set.

Key words: image fusion, fusion quality evaluation, total variation regularization, structural similarity, structure and texture decomposition

中图分类号: